Recommendation
-
Whose doctor does the AI recommend? An algorithm audit of reputation and demographic signals in large language model-assisted physician choice
2026-08-14 15:39:10Syeda Anshrah Gillani, Mirza Samad Ahmed BaigAbstract
Patients increasingly ask large language model (LLM) assistants which doctor to see, making these systems AI infomediaries: algorithms that intermediate one person's choice among other people and thereby decide, silently and at scale, which physicians become visible. We report a prespecified randomized algorithm audit of what causally moves those recommendations. Seven models (six open-weight; gpt-4o-mini) each chose among five synthetic family-medicine physician cards whose attributes were independently randomized across 3,024 choice sets, three patient personas, nine prompt paraphrases and nine experimental arms, yielding 40,068 scored responses; gender and ethnicity were signaled through names following correspondence-audit methodology. Reputation signals dominate: raising a rating from 3.9 to 4.7 increases choice probability by 31.4 percentage points (pp), and raising the fee from $90 to $190 lowers it by 20.0 pp. Demographic parity is rejected, but not in the direction human audit studies predict: female-signaled names gain 2.5 pp, and Hispanic-, South-Asian- and Black-signaled names gain 1.3-2.9 pp over White-signaled names, tilts worth $7-$14 per visit in fee-equivalent terms, and a content-free first-listed position is worth $11. Yet models mentioned gender or ethnicity in at most 0.03% of their stated reasons and abstained in 0.39% of trials, so these effects are invisible in the models' own explanations, and transparency obligations relying on model self-report would not detect them. One reasoning model failed the prespecified auditability gate outright. The frozen design makes the audit repeatable: any new model can be assessed against identical stimuli, making recurring behavioural audit, rather than self-reported explanation, the monitoring technology fit for purpose.
Abstract (translated)
URL
https://arxiv.org/abs/2608.14399
PDF
-
Seeing Red, Thinking Bad: Color Bias in Vision Language Models
2026-08-14 13:14:58Kohsuke Ide, Ryousuke Yamada, Yoshihiro Fukuhara, Hirokatsu Kataoka, Yutaka SatohAbstract
Vision language models (VLMs) are increasingly used in industrial decision-making systems, such as recruitment support and recommendation. This motivates careful analysis of how VLMs process visual and textual information. In this work, we study how VLMs interpret text rendered as an image, and investigate the influence of visual styling biases. To this end, we introduce Stealth Visual Prompts, which subtly change visual styling of text, such as color and contrast, while preserving semantic content. Using these prompts, we systematically control the visual styling of words in text and measure their impact on the analysis performed by VLMs. We further analyze how such visual perturbations affect the latent representations of the vision encoder. From our experiments, we observed that coloring positive words in green consistently shifts sentiment predictions toward a positive direction. As a result, VLMs often fail to properly account for negative words present in the text. Our analysis suggests that this behavior is correlated with changes in the latent representations of the vision encoder induced by color variations. In addition, we show that reducing text--background contrast increases reliance on visually salient cues and leads to more incorrect Visual Question Answering (VQA) outputs. These results suggest that the visual styling of rendered text can guide VLMs' interpretation in ways that diverge from human semantic understanding. Project page: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2608.14286
PDF
-
Rewrite Once, Validate Anywhere: Producing OWL-Aware SHACL Constraints
2026-08-14 09:06:10Anouk Oudshoorn, Piotr Gorczyca, D\"orthe ArndtAbstract
The Shapes Constraint Language (SHACL) is a W3C recommendation to express syntactic constraints, called shapes, on RDF graphs. SHACL validators are used to test whether a given graph adheres to such a shape. However, RDF graphs often come with OWL ontologies, whose implicit knowledge needs to be taken into account. This is classically handled by first applying reasoning and then performing the constraint checking on the results, often using different technologies which makes the process inefficient and vulnerable for mistakes. To overcome this, we propose to internalise the OWL axioms in the SHACL constraints; we construct a rewriting which takes as input both shapes and an OWL EL$^-$ ontology -- a fragment of OWL EL restricting the usage of existential restrictions -- and produces SHACL constraints. This output can then be evaluated by any validator supporting SHACL core regardless of its reasoning support, while yielding the same results as the traditional approach. The implementation of our translation is evaluated both against applying state-of-the-art reasoners and validators consecutively, as against validators with built-in reasoning support. For our benchmark, we show that our approach is in general more efficient in finding violations compared to the sequential approach, thus providing a powerful tool which simplifies combining reasoning with validation.
Abstract (translated)
URL
https://arxiv.org/abs/2608.14104
PDF
-
MACS: A Hybrid Multi-Agent Framework for Reliable Conversational E-Commerce Recommendation
2026-08-14 08:26:19Juli Huang, Hannah Clay, Sajjad Beygi, Thomas Sarda, Negin Golrezaei, Amin SaberiAbstract
Conversational recommendation for e-commerce is increasingly mediated by large language models (LLMs), yet many real-world deployments operate under a stricter requirement: recommendations must be drawn only from a merchant's fixed catalog, without web search or unsupported product claims. In this setting, the main challenge is reliability under hard constraints: the system must satisfy user requirements, remain grounded in available inventory, and preserve preferences across multiple conversational turns. We present MACS (Multi-Agent Commerce System), a hybrid multi-agent framework for reliable conversational recommendation in fixed-catalog settings. MACS uses LLMs for language-facing tasks such as interpreting user requests, eliciting preferences, and generating responses, while correctness-critical operations, including product retrieval, hard-constraint filtering, brand exclusion, and progressive relaxation, are executed deterministically by the merchant agent. A session-persistent preference layer tracks constraints across turns, enabling consistent handling of budget overwrites and exclusion reversals. On a 140-query single-turn benchmark, MACS achieves the highest pass rate (87.1%) and perfect brand compliance (1.000). On a 10-scenario multi-turn benchmark, MACS achieves the strongest macro Pass@5 (72% vs. 56% GPT+Catalog / 52% Gemini+Catalog) with zero constraint drift. The advantage is sharpest on exclusion reversal (100% vs. 20% / 0%) and constraint accumulation (100% vs. 60% / 40%). Mean judged response quality is similar across systems (0.751 vs. 0.736). These results suggest that hybrid architectures combining deterministic constraint enforcement with session-persistent preference tracking provide stronger reliability-oriented performance than catalog-bound prompt-only baselines in the fixed-catalog merchant setting.
Abstract (translated)
URL
https://arxiv.org/abs/2608.14068
PDF
-
Residual Dominance as a Structural Account of Last-Item Reliance in Causal Self-Attention Recommenders
2026-08-14 07:09:58Keito Kozaki, Keigo Sakurai, Ren Togo, Takahiro Ogawa, Miki HaseyamaAbstract
Transformer-based sequential recommenders with causal self-attention often rely heavily on the most recent interaction at inference time, but how this behavior is structurally expressed in the representation used for prediction remains unclear. We combine prediction-time diagnostics with norm-based analysis of the full attention block. First, we show that SASRec-style models exhibit highly localized last-item reliance. We then find that, although self-attention aggregates contextual information, residual addition sharply shifts the full-block representation toward same-position contributions, which we term residual dominance. To probe this interpretation, we use inference-time residual scaling as a controlled diagnostic intervention. Changing the residual strength induces a monotonic trade-off between structural mixing and last-item reliance, while reducing residual strength recovers a subset of final-position misses for which representations at non-final positions already rank the ground-truth item correctly. Our results provide a structural account linking extreme last-item reliance to residual dominance at inference time. The code is publicly available.
Abstract (translated)
URL
https://arxiv.org/abs/2608.14021
PDF
-
EchoRec: Multi-Item Prediction-Empowered Generative Recommendation via Cycle-Consistent Preference Alignment
2026-08-14 06:59:12Haokai Ma, Aoqi Hu, Yueao Xing, Ruobing Xie, Yonghui Yang, Teng Tu, Lei Meng, Tat-Seng ChuaAbstract
Generative recommendation autoregressively generates the semantic IDs of the target item, unifying preference modeling and index retrieval within the shared token space. Recent attempts have introduced Multi-Token Prediction (MTP) into this field, yet they primarily inherit its efficiency merit, leaving its potential as dense supervision unexplored. Unlocking this potential hinges on whether future behaviors qualify as informative supervision. Our analysis reveals that future behaviors carry a semantic echo of the current one far above that of random pairs, which nevertheless decays along horizons under intent transitions, making them informative yet order-dependent signals. Motivated by this, we propose EchoRec, which empowers MTP with cycle-consistent holistic preference alignment across multi-horizon for generative recommendation. It comprises two synergistic modules. Horizon-aware Preference Generation (HPG) sequentially chains lightweight auxiliary branches upon the base recommender, where each branch conditions on its predecessor to respect preference evolution. Verifiable Holistic-Preference Alignment (VHA) further consolidates them into the holistic preference and echoes it back through cycle-consistent projectors to suppress spurious alignment, with theoretical guarantees that exclude the rank-collapse form of spurious alignment under an invertible transport, enabling the holistic preference to be retained in the decoding representation. All auxiliary components serve as disposable scaffolding discarded at inference, introducing negligible online serving overhead. Extensive experiments on three datasets demonstrate the superiority of our EchoRec, together with its naturally acquired multi-item generation ability. Our code and datasets will be available upon acceptance.
Abstract (translated)
URL
https://arxiv.org/abs/2608.14011
PDF
-
Content Depth Matters in Short-Video Recommendation: Rethinking the Attention Economy
2026-08-14 06:13:40Liwei Deng, Jing Jiang, Zhiwei Li, Yang Wang, Guodong LongAbstract
Driven by the attention economy, short-video Recommender Systems (RSs) are primarily optimized to maximize user engagement by promoting videos that capture attention within seconds. These systems inherently favor shallow-content videos that are effective at attracting immediate attention. However, growing evidence suggests that prolonged exposure to such content may negatively affect users' cognitive engagement and mental well-being, raising concerns about the long-term societal impact of the short-video platform. To tackle this challenge, this paper introduces a new metric, the \textbf{Content Depth Score (CDS)}, to quantify the content depth of short videos. CDS measures the extent to which a video is expected to stimulate higher-order cognitive processes, using a seven-level scale grounded in established theories of cognitive psychology and learning. As an initial step toward this vision, we present \textbf{SCOPE-Bench}, the first benchmark for content-depth evaluation in short-video recommendation. Built upon a large-scale open-source short-video dataset, SCOPE-Bench provides CDS annotations for 150K videos, enabling systematic evaluation of RSs from a cognitive-content perspective. Leveraging SCOPE-Bench, we evaluate 13 representative RSs and reveal a consistent preference for shallow-content videos. Moreover, we find that these algorithms recommending cognitively deep content are only marginally better than random selection, highlighting a previously overlooked limitation of existing recommendation objectives. Our code and datasets are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.13990
PDF
-
BiasMix-Finance: Post-Generation KYC Guardrails for LLM Portfolio Advice
2026-08-14 05:32:14Gaurav Kukreja, Parul Kukreja, Mohammed Abraar, Raj Dandekar, Rajat Dandekar, Sreedath PanatAbstract
Large language models (LLMs) can generate plausible-sounding ETF portfolios while silently violating basic KYC-style constraints on risk, fees, and diversification. This is especially problematic in agentic multi-turn advisory systems, where each draft recommendation can become an action unless guarded by an auditable enforcement layer. We study a model-agnostic, asset-agnostic post-generation guardrail pipeline: (i) enforce a strict JSON allocation schema, (ii) validate allocations against numeric caps, and (iii) when violations occur, deterministically project the output to the nearest feasible portfolio via a convex quadratic program (QCQP). We introduce BiasMix-Finance (Mini), a compact stress-test benchmark for constrained decision-making under biased LLM generations, with a 16-ETF universe, three investor profiles, and eight bias prompts. Across three models and three inference modes (direct, critique, self-consistency), first-pass generations violate at least one cap in 47.6-85.7% of test cases (67.2% pooled), but the convex projection layer reduces final feasibility violations to 0% while requiring only a small correction distance (test pooled median D=||w*-w0||_2=0.066), indicating that the guardrail typically preserves the intent of the original allocation. We report violation rates and correction distances with confidence intervals, and paired model comparisons with multiple-testing correction. To support reproducibility, we release the dataset, prompts, caps, and code in our public GitHub repository.
Abstract (translated)
URL
https://arxiv.org/abs/2608.28646
PDF
-
RAIL: An Automatic Classifier of the Artificial Intelligence Readiness Level
2026-08-13 16:17:41Juan Irving Vasquez, Juan Terven, Laura-Ivoone Garay-JimenezAbstract
Assessing the maturity of artificial intelligence technologies is essential for investment decisions, project management, and policy monitoring, yet the available readiness frameworks are heterogeneous and difficult to apply automatically: the adaptation of Technology Readiness Levels to AI lacks AI-specific gating criteria, the Machine Learning Technology Readiness Levels presuppose access to internal process artifacts, and AI/data readiness dimension models employ scales that resist direct comparison. This paper makes two contributions. First, we unify these three frameworks into the Unified AI Readiness Level (AIRL), a nine-level ordinal scale built on an environmental evidence ladder and complemented by dimensional caps (covering specification, data existence, data quality, data legality, expert knowledge, and algorithmic maturity) together with a generality-anchoring rule and explicit assignment disciplines, so that a readiness level becomes decidable from a natural-language description of the work alone. Second, we propose RAIL (Readiness Assessment via Independent LLM-experts), a panel-of-experts classifier that operationalizes the scale: one evidence agent and six independent dimension agents, each a large language model with a narrowly scoped mandate, deliver verdicts that a deterministic minimum rule aggregates and a chief expert reviews under asymmetric authority, confirming or lowering the panel's recommendation but never raising it above the caps. The method was tested in the analysis of several research works showing consistency and avoiding overestimation from monolithic LLM classifiers.
Abstract (translated)
URL
https://arxiv.org/abs/2608.13428
PDF
-
Numeracy in Large Language Models: Fundamental Limitations and Paths to Improvement
2026-08-13 12:01:58Aoxin NiAbstract
Large language models (LLMs) achieve strong results on mathematical reasoning benchmarks yet remain unreliable on elementary numerical tasks, including magnitude comparison, large-integer arithmetic, fractions, and scientific notation. This survey examines basic numerical understanding as a capability distinct from high-level mathematical reasoning. We propose the Numerical Grounding Framework (NGF), which decomposes numeracy into Representational Grounding (RG), mapping numeral forms to value, magnitude, and equivalent representations, and Procedural Grounding (PG), executing arithmetic operations in accordance with their mathematical definitions. Using NGF, we organize recent diagnostic benchmarks, failure modes, structural explanations, and mitigation strategies. We review evidence concerning tokenization, positional encoding, embedding geometry, and pretraining-data distribution. We also apply NGF in a coordinated evaluation of three frontier model families across Number Cookbook, NumericBench, and GSM-Symbolic, comparing atomic, contextual, and reasoning-assisted numeracy. Architectural interventions such as digit-aware tokenization and Abacus Embeddings can improve models trained from scratch but are generally unavailable to users of pretrained systems, for whom supervised fine-tuning, reasoning scaffolds, and external tools are more practical. We conclude with deployment recommendations and research directions for more reliable numerical behavior in foundation models.
Abstract (translated)
URL
https://arxiv.org/abs/2608.13129
PDF
-
FSGR: Mitigating Token Frequency Bias for Fair SID-Based Generative Recommendation
2026-08-13 05:34:51Yuchen Zheng, Sihan Xu, Jingwen Yang, Xiangrui Cai, Haiwei Zhang, Xiaojie YuanAbstract
Semantic ID (SID)-based generative recommendation has recently achieved remarkable success. However, existing methods suffer from a previously overlooked fairness issue, which we term \textbf{Token Frequency Bias}, where high-frequency SID tokens are systematically over-predicted while low-frequency SID tokens are under-predicted. This bias originates from the combined effects of imbalanced semantic codebooks during SID construction, and popularity bias together with the maximum likelihood estimation objective during recommendation training, resulting in unfair exposure across item categories. Existing SID methods mainly focus on improving codebook quality and overlook the impact of token frequency imbalance on downstream recommendation fairness, while LLM debiasing methods often yield suboptimal results when directly applied to SID-based recommendation, due to the hierarchical semantics of SID tokens. To address this issue, we propose \textbf{FSGR}, a fairness optimization framework for SID-based generative recommendation. During SID construction, FSGR employs OT-based Assignment Optimization and Dual-Criteria Re-anchor mechanism to form a more balanced SID representation space. During recommendation training, it adopts a two-stage training strategy and introduces Hierarchical Frequency Calibration for layer-specific fairness fine-tuning. Experiments on three public datasets with three backbone models demonstrate that FSGR mitigates token frequency bias and delivers an average Gini fairness improvement of over 20\% while maintaining competitive recommendation accuracy.
Abstract (translated)
URL
https://arxiv.org/abs/2608.12845
PDF
-
Fast A/B/n Testing: Exact Multi-Policy Comparison via Tree-Coupled Feedback Sharing
Abstract
Online platforms increasingly compare many adaptive decision policies---ranking systems, recommendation algorithms, pricing rules, and language-model agents---while each reward-bearing interaction can be costly or risky. A direct A/B/n design gives each of $J$ policies its own horizon-$T$ trajectory and therefore uses $JT$ outcomes. We introduce Tree-Coupled A/B Testing (\TCAB), an exact feedback-sharing design for arbitrary history-dependent contextual-bandit policies. At each round, a predictable tree connects the current policy histories; every parent--child context--action law is maximally coupled, and one reward is shared within each component of matched tree edges. Every policy retains exactly its standalone finite-horizon trajectory law, even though the policies are deliberately dependent. If $D_{e,t}$ records a mismatch on tree edge $e$ at round $t$, the number of reward queries satisfies the pathwise identity $N(T)=T+\sum_{t,e}D_{e,t}$ and hence equals $T$ plus cumulative tree-edge total variation in expectation. This cost is conditionally optimal among exact edge-local designs on the selected tree, and a current-round minimum-spanning tree is myopically optimal among tree designs. For fixed $J$, sublinear pseudo-regret of every policy and almost-sure uniqueness of the oracle action imply $\mathbb{E}[N(T)]=T+o(T)$, versus $JT$ for independent runs. We also obtain finite-sample variance bounds for pairwise policy contrasts. Experiments on reward-model evaluation, multiple-choice language-model evaluation, and adaptive search policies demonstrate substantial improvements in the cost--precision frontier.
Abstract (translated)
URL
https://arxiv.org/abs/2608.12831
PDF
-
How to Spend Your Oracle Budget: Practical Guidance for Protein Structure Prediction Models
2026-08-12 15:46:57Aleksandra Kalisz, Jack Simons, Krisztina Sinkovics, Noam Ghenassia, Shikha Surana, Henry Moss, Paul DuckworthAbstract
Foundation models for protein structure prediction remain unreliable on certain targets. External oracles can flag and correct these failures, but biological oracles are expensive, making oracle budget a critical constraint. Existing guidance methods, such as FK-steering, DPO, and Best K-of-N sampling, differ in how they spend this budget, yet no systematic comparison exists to guide method selection. To bridge this gap, we benchmark these methods alongside the recently proposed Optimisation Over Outputs (O3), which applies off-the-shelf optimisers within a generative model's latent subspace. We extend the usage of O3 to protein structure prediction models. Overall, our work provides the first practical reference for oracle budget-aware guidance. Our evaluation on two protein targets, calmodulin (1CLL) and E. coli aspartate transcarbamoylase (9EEH), reveals that no single method consistently dominates across all budgets and oracles. Specifically, O3 proves most effective at low oracle budgets, while FK-steering and DPO demonstrate improved performance as the budget increases. We distil these findings into actionable recommendations for practitioners operating under real-world oracle-budget constraints.
Abstract (translated)
URL
https://arxiv.org/abs/2608.12192
PDF
-
HCGRec: Hint-Conditioned Generative Recommendation with Semantic IDs
2026-08-12 12:13:08Kangning Zhang, Haotian Fang, Xukun Luo, Hao Yin, Yang Gao, Peng Yan, Weiwen Liu, Weinan Zhang, Yong YuAbstract
Semantic-ID generative recommenders represent each item as a short sequence of discrete semantic tokens and predict the next item by autoregressively generating this token sequence. This paradigm enables a unified generation interface for item IDs, histories, and item text, but it also creates a structured optimization bottleneck during reward-based post-training: when an early semantic token enters the wrong branch of the item-token space, finite rollout groups rarely reach the ground-truth item, so group-relative optimization receives identical zero rewards and produces no useful advantage. We propose Hint-Conditioned Generative Recommendation (HCGRec), a semantic-ID generative recommendation framework that recovers learning signal for such hard training instances. HCGRec diagnoses each instance with checkpoint rollouts and supplies a minimal target-prefix hint only when the current generator cannot reach the correct item. The model then generates the unhinted suffix under the hinted semantic branch, turning zero-reward groups into informative comparisons over item-token completions. Hinting also changes token identity: hinted prefix tokens are oracle-provided item context, while unhinted suffix tokens are sampled generation actions. We therefore introduce hint-aware credit decomposition, using supervised learning to preserve item-semantic and prefix-structure alignment for hinted tokens and GRPO to optimize the sampled suffix. Experiments on sequential recommendation benchmarks show that HCGRec substantially improves over supervised fine-tuning and vanilla reward-based post-training, while reducing zero-advantage training samples from over 70% to below 20%. The code is accessible at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.11980
PDF
-
GRPO for Financial Advice Generation: Outperforming Commercial LLMs under CATE Evaluation
2026-08-12 08:28:15Ofir Ben Shoham, Shrutendra Harsola, Vignesh Subrahmaniam, Shravan Mohan, Yakov Gazman, Oded VainasAbstract
Generating actionable financial advice from business records demands that models integrate numerical reasoning, domain knowledge, and sound judgment, while avoiding recommendations that could harm the business. Direct supervision is difficult: historical decisions are not necessarily optimal, and high-quality free-form labels are expensive to obtain. We formulate financial advice generation as a reinforcement learning problem and fine-tune an open-weight language model using Group Relative Policy Optimization (GRPO). Our reward is an LLM-as-a-judge rubric that scores each recommendation across multiple binary dimensions of advice quality, augmented with a safety gate for harm prevention. Since LLM-based evaluation alone cannot confirm whether improvements reflect genuine business value rather than adaptation to the judge, we complement it with a judge-independent audit based on a standard doubly-robust Conditional Average Treatment Effect (CATE) estimator. Under this observational off-policy audit, our trained LLM achieves approximately twice the estimated gross-profit lift of the strongest evaluated commercial baseline ($0.0228$ vs.\ $0.0104$), together with the lowest downside rate and the least negative tail risk of any policy evaluated. Notably, the two evaluations do not rank the baselines identically: the untrained base model places last on the judge rubric but second on the causal audit, indicating that the audit captures a signal the judge does not. Our results demonstrate that GRPO with a finance-grounded reward signal can produce substantially more useful business recommendations than commercial LLMs, and that a judge-independent causal audit is a valuable complement to, rather than a confirmation of, LLM-as-a-judge assessment in financial NLP.
Abstract (translated)
URL
https://arxiv.org/abs/2608.11787
PDF
-
Locating and Controlling Implicit Personalization in Large Language Models
2026-08-12 07:18:31Yueru Yan, Siqi Wu, Thai LeAbstract
Large language models (LLMs) often shift their outputs in response to implicit demographic cues even when users never state a demographic identity. Previous work has documented this behavior, but the connection between these behavioral changes and the model's internal activations remains unclear. Using matched cued and neutral conversations across five LLMs, we establish that a localized internal activation signal tracks changes in recommendations, with correlations up to r=0.87. When multiple cues appear together, their internal signals largely combine, but the changes in output do not simply add up. We further show that removing the internal signal associated with one cue can suppress its influence, often more effectively than asking the model to ignore demographics via prompting, while largely preserving general benchmark performance. However, the ability to selectively remove one dimension's influence while leaving co-present dimensions intact remains highly model- and attribute-specific. These results connect implicit personalization behavior to an internal signal that can be analyzed and causally controlled.
Abstract (translated)
URL
https://arxiv.org/abs/2608.11735
PDF
-
Learning from Online User Feedback for Shopping Agents
2026-08-12 03:24:44Haobo Zhang, Kelong Mao, Sulong Xu, Simiu Gu, Zhicheng DouAbstract
Large language model-based shopping agents are increasingly deployed in real-world e-commerce platforms, generating massive amounts of user interaction logs that provide valuable supervision for improving these agents. However, existing approaches primarily rely on offline training signals, such as user-item interactions or synthetic preference data, while largely overlooking the rich supervision contained in users' natural conversational feedback. Moreover, the available online feedback is heterogeneous, sparse, and noisy, making it difficult to transform into reliable learning signals automatically. To address these challenges, we propose LOFA, a framework that enables shopping agents to learn directly from real online interaction logs without human annotation. LOFA combines reinforcement learning over verifiable purchase outcomes with feedback-aware on-policy distillation, which identifies users'in-dialogue directives and converts them into dense token-level supervision. These complementary objectives capture both collaborative behavioral patterns and user-specific preferences. Extensive experiments on real-world e-commerce logs demonstrate that LOFA consistently improves recommendation quality, response helpfulness, and user-satisfaction alignment over strong baselines, highlighting the effectiveness of learning shopping agents from real online user feedback.
Abstract (translated)
URL
https://arxiv.org/abs/2608.11604
PDF
-
From Prompting to Behavioral Alignment: Personalized LLM Judges for Recommendation Evaluation
2026-08-11 23:06:39Alireza S. Ziabari, Kat Ellis, Colleen Chan, Ding TongAbstract
Traditional offline recommendation evaluation relies heavily on complex, manually maintained feature pipelines that are difficult to scale. While Large Language Models (LLMs) offer a promising alternative by predicting user engagement directly from raw text logs, empirical analysis in this study identifies a critical failure mode termed bidirectional rationalization. In a zero-shot setting, LLMs are found to convincingly argue for both positive and negative user engagement outcomes on the exact same item with identical evidence, highlighting the unreliability of off-the-shelf LLMs in predicting user engagement. To resolve this, we develop and apply a sequential behavioral alignment framework pairing fine-tuning with preference optimization over paired correct and counterfactual rationales. Evaluated on real-world homepage interaction logs, this aligned reasoning approach achieves a 32.19\% lift in Macro-F1 score over the zero-shot baseline and matches the production feature-engineered baseline. The results demonstrate that behavioral alignment mitigates bidirectional rationalization while delivering human-interpretable reasoning traces without manual pipeline overhead.
Abstract (translated)
URL
https://arxiv.org/abs/2608.11493
PDF
-
Inverse Theory of Mind Modeling for Content Recommendation: From Web Browsing to Dynamic Intelligent Interfaces
2026-08-11 18:58:28Mengyu Chen, Feiyu Lu, Chun-Fu Chen, Lucas Vinh Tran, Jay KatukuriAbstract
Modern recommender systems treat observed actions as reliable proxies for user preferences, yet interactions often reflect exploration or comparison rather than stable preference expression. As interfaces evolve from static layouts toward generative UIs and immersive extended reality (XR), the need for deeper, modality-agnostic user understanding grows: these adaptive environments must decide not only what to present but where, when, how prominently, and most importantly why a user acts. We propose an Inverse Theory of Mind (IToM) pipeline that reasons backward from observed interactions to infer the beliefs, preferences, and decision-making traits that explain behavior. The pipeline reconstructs each user's decision context, including what was chosen and what alternatives were available, applies LLM-driven counterfactual reasoning to produce evidence-grounded natural-language belief statements, and synthesizes these beliefs through multi-hypothesis abductive inference into a structured user persona. We evaluate on the OPeRA dataset against ground-truth personality assessments, attitudinal surveys, and interview-based personas across four tasks: next action prediction, shopping attitude alignment, Big Five personality inference, and held-out category prediction. Results show that inferred personas match or exceed ground-truth personas and that multi-hypothesis reasoning is essential for accurate personality prediction. We further demonstrate cross-modal transferability with a persona-driven spatial banking application on VisionOS.
Abstract (translated)
URL
https://arxiv.org/abs/2608.11354
PDF
-
RTSKG: Building a Rail Transit Station Knowledge Graph Dataset
2026-08-11 15:41:34Shutong Zhu, Tianxing Wu, Runfeng Liu, Yuang Gu, Xuan He, Yuan ZhuAbstract
Rail transit systems play a vital role in urban mobility and economic development. As key components of such systems, rail transit stations function as critical transport hubs that enhance urban accessibility and stimulate development in surrounding areas. City-level rail transit station related tasks (e.g., ridership prediction) require large-scale urban data, but current studies often neglect complex interactions among various urban entities in terms of data organization. In this paper, to address the above issue, we build a Rail Transit Station Knowledge Graph (RTSKG) dataset which explicitly models the spatial and semantic interactions among different kinds of urban entities, to benefit city-level rail transit station related tasks. RTSKG integrates heterogeneous urban entities, such as rail transit stations, road segments, and points of interest, with a specially designed unified schema, and is accessible as Linked Data at this https URL. Evaluations on station-area store recommendation and knowledge-enhanced ridership prediction demonstrate the effectiveness of RTSKG, highlighting its potential to support city-level rail transit station analysis.
Abstract (translated)
URL
https://arxiv.org/abs/2608.11080
PDF
