Relation
-
Behavioral Couplings: From Formation to Behavioral Emergence in Language Models
2026-10-16 17:58:08Dongyoon Hahm, Woogyeol Jin, Dennis Wei, Yi Zhou, Nathalie Baracaldo, Kimin LeeAbstract
Fine-tuning large language models (LLMs) can induce behaviors beyond those explicitly targeted. For example, training a model to respond more warmly can make it more sycophantic, and training it to write insecure code can cause broad misalignment on prompts unrelated to coding. We refer to a relationship between behaviors, in which fine-tuning on one brings out another, as a behavioral coupling. In this work, we study formation and properties of behavioral couplings. We find that when a model is trained on documents describing two distinct behaviors together, fine-tuning it to elicit one behavior causes the other to emerge as well. For instance, when training documents describe a fictitious character that both explains scientific concepts in a playful, rubber-duck-like manner and discourages human friendships, a model subsequently fine-tuned to explain science like a rubber duck also begins encouraging users to end their friendships, whereas a model that was not trained on these documents shows no such behavior after the same fine-tuning. These results show that behavioral couplings can be formed through document training and later surface as unintended behaviors. More concerningly, we find that couplings can compose. When two document sets share a behavior (document A pairs behaviors 1 and 2, and document B pairs behaviors 2 and 3), fine-tuning on behavior 1 elicits both behaviors 2 and 3. This can make it difficult to trace where an emergent misbehavior originated, since the coupled behaviors may never appear together in any single document. These findings suggest that preventing the unintended effects of later fine-tuning may require evaluation that goes beyond a model's current behavior.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23847
PDF
-
Beyond Multi-Stage Pipelines: A Label-Correlation Ensemble for Multi-Label Retinal Fundus Disease Classification
2026-10-16 16:54:48Md Asif Uddin, Jannatul Ferdous, Asif Islam, Zobaer Mahmud Zisan, Promit Ghosh, Shah Ahafik Arman, Niloy Farhan, Rafeed RahmanAbstract
Retinal fundus images frequently carry more than one disease, and public fundus datasets are heterogeneous and severely long-tailed. Clinical triage suggests a staged design, in which a screening gate, a disease-group router and group-specific classifiers operate in sequence, but it is unclear whether this hierarchy earns its complexity. We present a controlled comparison of three architectures on a unified 39-target label space built from RFMiD 1.0, RFMiD 2.0 and ODIR-5K (12,652 images): (i) a three-stage gated cascade of eight models, (ii) a flat model with 39 independent sigmoid outputs, and (iii) a label-correlation model that replaces the flat linear head with 39 learned label queries and a two-layer transformer decoder. All three share one Swin-V2-B backbone, one preprocessing pipeline and one training protocol, so differences are attributable to the architecture. Staging offers no consistent advantage: tracing every missed disease instance to the stage that lost it shows that the two coarse gates discard 34.2% of true instances while the fine-grained classifiers lose only 6.7%, and the gates' hard zeros depress the cascade's macro-AUC to 0.747. Label-correlation modeling gives the largest single gain, raising the detection rate from 0.621 to 0.682 (0.689 with test-time augmentation). Blending the flat and label-correlation models under four-view test-time augmentation is the best configuration on six of eight metrics (exact match 0.694, micro-F1 0.678, macro-F1 0.456, macro-AUC 0.972). On definition-matched class subsets it matches or exceeds four recent studies on macro- and micro-F1, most clearly on low-support pathologies. We also show that ensembling a gated cascade with continuous-output models is harmful, and that per-source negative sampling is needed to remove a dataset shortcut that otherwise yields a spurious AUC of 1.000.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23747
PDF
-
Interpreting SSL Representations for Spoof Detection: a WavLM Study
2026-10-16 14:26:55Mohamed Mallat, Michele Panariello, Massimiliano Todisco, Nicholas Evans, Anthony LarcherAbstract
Self-supervised speech models such as WavLM achieve strong spoofing detection performance, yet which layers encode the most spoof-relevant information and what acoustic properties they capture remain opaque. We present a layer-wise interpretability study of WavLM using the ASVspoof 5 database, combining three complementary analyses: (i) per-layer linear probing with attack-level evaluation across speech synthesis, voice conversion, and adversarial attacks; (ii) a canonical correlation analysis (CCA) linking layer representations to spoofing-relevant acoustic features; (iii) an exhaustive grid search over layer subsets showing that use of five layers outperforms full thirteen-layer pooling. CCA analysis reveals that, while most acoustic features peak in alignment with mid-layers and then decay, voice quality measures jitter, shimmer, and the harmonics-to-noise ratio show the opposite trend, with correlation increasing toward later layers. Embedding visualisations reveal that deeper layers capture a continuous acoustic similarity among attacks rather than discrete categories, suggesting these layers encode fundamental synthesis artifacts rather than attack-specific signatures.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23526
PDF
-
S-GAP: Stealthy Graph Attack Primitives for Graph Large Language Models
2026-10-16 13:45:23Wenda Li, Tongya Zheng, Shunyu Liu, Hanyang Yuan, Kaixuan Chen, Yu Wang, Yuchen Ying, Haoze Jiang, Huan Li, Gang Chen, Zujie RenAbstract
Graph Large Language Models (GraphLLMs) enable powerful semantic understanding and reasoning over Text-Attributed Graphs (TAGs), while their semantic reasoning may exhibit vulnerabilities to perturbations in node text and graph structure under adversarial attack evaluation. Existing attacks typically construct textual and structural perturbations in separate stages guided by distinct realization intents. However, this separation results in attack-intent fragmentation, causing semantic incoherence between the two perturbation types, thereby undermining attack stealth and making them easier for GraphLLMs to identify and disregard, ultimately weakening attack effectiveness. To avoid attack-intent fragmentation, we propose the Graph Attack Primitive (GAP), an atomic semantic representation that unifies textual and structural perturbations under a coherent attack intent. By carefully calibrating the semantic composition of a GAP, we can achieve strong attack effectiveness while maintaining sufficient attack stealth. Furthermore, we introduce S-GAP (Stealthy GAP), a multi-agent framework that iteratively refines the semantic content of the GAP. The framework unifies GAP planning and realization and continuously refines this process through surrogate evaluation and textual feedback. Extensive experiments across four datasets, three GraphLLMs, and two attack settings show that S-GAP improves ASR over the strongest baselines by 7.02% on average while producing more relationally plausible perturbations, exposing critical vulnerabilities in current GraphLLMs and motivating more robust defenses.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23465
PDF
-
Through the PRISm: Importance-Aware Scene Graphs for Semantic Image Retrieval
2026-10-16 12:53:21Dimitrios Georgoulopoulos, Nikolaos Chaidos, Angeliki Dimitriou, Giorgos StamouAbstract
Web-based visual search increasingly handles queries driven by semantic intent, focusing on what is happening in an image rather than merely what it looks like. While global embeddings from vision-language models capture overall appearance, they often blur fine-grained relational structure. Conversely, scene graphs make these relationships explicit, but generating them automatically for unannotated web images produces dense, noisy graphs that retain every detected entity and relation regardless of relevance. To address this, we introduce PRISm (Pruning-based Image Retrieval via Importance Prediction on Semantic Graphs), an image-to-image retrieval framework that learns to focus on what matters in a scene. PRISm employs an Importance Prediction Module, supervised by caption-derived relevance strictly during training, to score and prune non-essential objects and <subject, relation, object> triplets. An Edge-Aware Contextual GNN then aggregates relation conditioned neighbor messages, fusing the refined graph with global visual features into a single, index-ready embedding per image. On PSG, PRISm outperforms the strongest baseline by points in MAP@1. Furthermore, on Flickr with machine-generated scene graphs and captions, PRISm remains best on top-1 metrics, while adding only 33,ms per query beyond scene graph generation.
Abstract (translated)
URL
https://arxiv.org/abs/2512.18407
PDF
-
AWAM: Active Trajectory-Conditioned View Imagination for Robust Robot Manipulation
2026-10-16 12:53:08Jiawei Geng, Zhenyang Liu, Yuzheng Wu, Yanwei FuAbstract
Rapid progress in embodied intelligence has enabled increasingly capable robots to follow language instructions and manipulate diverse objects. However, strong results in structured environments do not automatically transfer to open-world conditions, where clutter, occlusion, and changing viewpoints can obscure the spatial relationships required for action. To address this perceptual gap, a virtual active-perception paradigm is introduced. AWAM, an Active World-Action Model actively plans where to observe and imagines what will be seen along the planned trajectory before acting. Task-related virtual camera motion is predicted and used as a structured query into a geometry-conditioned world model, producing a reusable spatial prior for manipulation, which is later compressed into a fixed memory and fused with live observations through cross-attention for diffusion-based action prediction. AWAM achieves competitive success rates with 75.9% on LIBERO-Occ, 62.4% on LIBERO-Plus, 76.5% on RLBench-OG Occlusion1, and 94.4% in real-robot trials. These results support improved robustness to the evaluated occlusions and distribution shifts, addressing part of the gap between structured manipulation and less controlled environments.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23396
PDF
-
UniPolar: Joint Image and Polarimetric Restoration under Compound Degradations via Physical Consistency Learning
2026-10-16 12:07:08Yang Jin, Guangyu Guo, Linghao Shen, Binglu WangAbstract
Polarimetric image restoration aims to recover polarization angle images and reliable polarimetric quantities from degraded observations. Beyond visual fidelity, it also requires preserving the physical relationships underlying reliable polarimetric estimation. However, existing methods typically address either device- or environment-induced degradations in isolation, limiting their applicability to color polarization filter array (CPFA) imaging, where both often coexist. Such compound degradations jointly perturb image intensities and cross angle polarization differences. Consequently, improved image fidelity alone does not necessarily ensure accurate Stokes, DoLP, and AoLP recovery. To address this challenge, we propose UniPolar, a coupled Image Stokes framework for joint image polarimetric restoration from compound-degraded CPFA observations. Specifically, UniPolar employs two complementary streams to reconstruct four polarization-angle images and directly predict Stokes difference components. To coordinate these streams, Degradation Conditioned Cross Domain Interaction combines Dual Domain Frequency Interaction for frequency selective evidence exchange with Degradation Conditioned Modulation for condition adaptive feature correction. Furthermore, at the output level, Image Stokes Physical Consistency Learning aligns image derived and directly predicted Stokes components while regularizing angular fidelity and the physical feasibility of DoLP. On the compound-degradation benchmark, UniPolar achieves average image and DoLP PSNR of 31.522 dB and 24.097 dB, respectively, with an average AoLP error of 16.833 degree. These results underscore the importance of jointly considering visual fidelity and polarimetric reliability, offering a physically grounded perspective on learning based restoration under compound degradations.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23360
PDF
-
Dependency Reasoning for Aspect Sentiment Quadruple Prediction
2026-10-16 12:03:17Shima Esfandyari, Seywan Soleymanbaigi, Fardin Akhlaghian Tab, Fatemeh Daneshfar, Mourad OussalahAbstract
Aspect Sentiment Quadruple Prediction (ASQP) is fundamentally a relational reasoning problem: identifying aspect-opinion-category-sentiment quadruples requires modeling structured dependencies, not merely sequential co-occurrence. Existing LLM-based approaches incorporate syntactic information indirectly, via retrieval-based demonstration selection or multi-stage training, rather than as unified, single-pass generation-time context. We present DRIFT, which linearizes dependency parse trees and injects them directly into LLM prompts as explicit relational context, enabling the model to reason over aspect-opinion dependencies rather than infer them from token proximity alone. DRIFT further integrates retrieval-augmented in-context learning and a syntax-aware LLM-based adjudication mechanism that complements exact-match evaluation under span-boundary variation. On SemEval Rest15, Rest16, and ACOS, DRIFT achieves the strongest performance among compared generative ASQP methods, reaching 54.47% and 64.10% F1 on Rest15 and Rest16, with consistent gains across short- and medium-distance aspect-opinion configurations; adjudication further shows exact-match metrics systematically underestimate semantically correct predictions.
Abstract (translated)
URL
https://arxiv.org/abs/2610.14873
PDF
-
SimOPD: Relational Knowledge Transfer for On-Policy Distillation
2026-10-16 11:10:21Kai Tang, Xing Zheng, Haobo Wang, Guangcheng Zhu, Shenzhi Yang, Zhengqing Zang, Yingfan Ma, Bowen Song, Weiqiang WangAbstract
A key challenge in on-policy distillation (OPD) is extracting effective supervision from teacher knowledge. Supervision from token probabilities may underutilize internal knowledge, while direct hidden-state matching forces the student to shift to the teacher's feature space and complicates cross-architecture transfer. Inspired by contrastive learning's use of relationships between instances, we propose \textbf{SimOPD} to transfer teacher internal knowledge through response similarities. Specifically, SimOPD uses paired memory banks of student-generated responses to extract supervision from the teacher's internal representations as similarity distributions. The student then matches these distributions within its own representation space, retaining representational freedom and removing the need for cross-model projection. Extensive experiments show that SimOPD improves the overall average over the strongest baselines by up to 2.6 and 3.1 percentage points in same- and cross-architecture settings.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23306
PDF
-
Look, Reason, Draw a Region: Recursive Refinement for Spatial Context Prediction
2026-10-16 11:06:34Wajeeha Tahir, Anna Tegon, Lionnus Kesting, Gamze \.Islamo\u{g}lu, Krist\'of Karacs, Luca Benini, Thorir Mar IngolfssonAbstract
Spatial context prediction requires visual grounding and spatial reasoning to identify vacant regions relative to objects in a scene. Spatial relationships and physical constraints remain challenging for large vision-language models (VLMs). Recursive reasoning has demonstrated strong performance on discrete and abstract reasoning tasks, motivating its use for improving spatial context prediction in natural images. Weight sharing enables higher accuracy with a small trainable parameter count. We introduce Spatial-TRM, a compact recursive model with frozen vision-language features, a convex region decoder, and just 11.2M trainable parameters. This weight-tied reasoner supports six spatial relationships, three reference frames, and open-vocabulary anchor objects. On the RoboSpatial-Home benchmark, Spatial-TRM achieves 29.51% context accuracy, a gain of 9.02 percentage points (44.0% relative) over a separately trained single-step model with the same parameter count. Including the frozen encoders, the model has 877.8M total parameters, approximately $15\times$ fewer than the reported 13B size of RoboPoint. These results show that repeated refinement improves spatial context prediction from pretrained vision-language features at a fixed trainable parameter count on this benchmark.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23302
PDF
-
Can the Parts Fool the Test? Counterfactual Pairing Cycles for Relational OOD
2026-10-16 10:22:00Yibo Zhou, Yirong XiangAbstract
Relational out-of-distribution errors are easy to describe and hard to evaluate cleanly. An image may be natural, a caption may be fluent, and all mentioned objects may be common, yet the caption may describe the wrong relation in the image. Many evaluations intended to test this behavior can be solved without checking the pairing at all, because negatives differ in caption style, template, length, object frequency, or image statistics. We propose counterfactual pairing cycles, a blocked evaluation primitive that reuses the same two images and the same two captions on both sides of the comparison, changing only which image is paired with which caption. This makes image-only, text-only, and additive component shortcuts cancel exactly in finite samples. The same contrast also gives a training loss for relational outlier exposure and a diagnostic for bilinear vision-language scores. Across synthetic controls, GQA, and COCO, cycles separate coarse image-caption matching from directional role-binding failures, while also identifying geometric size relations that remain strongly visible in global features. In a shortcut-contaminated COCO outlier-exposure stress test, a model selected by a near-perfect shortcut validation AUROC retains substantial relational signal but remains below cycle training on exact cycles; cycle training improves CycleAcc from 0.882 to 0.927. The main lesson is simple: to test whether a model understands a pairing, the benchmark should keep the parts fixed, change the pairing, and ask only about coupling. The official implementation is available online.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23248
PDF
-
Validating LLM-generated political networks with survey-reported partisan exposure
2026-10-16 09:38:11Marco Tonin, Michele Tizzoni, Bruno Lepri, Luca Maria AielloAbstract
Large language models (LLMs) are increasingly used to simulate human behavior in social science research, including decisions, interactions, and social relationships. However, in network formation tasks, existing evaluations often focus on aggregate network properties, while networks with plausible structural properties may still fail to reproduce individuals' social and political environments. Here, we generate LLM-based political networks using personas sampled from the nationally representative ANES 2020--2022 Social Media Study and use respondents' survey-reported partisan exposure as an empirical benchmark for the political environments generated for the corresponding personas. We first characterize the structural properties and political assortativity of the generated networks, and then compare ego-level partisan exposure with the survey. We find that the structure and political assortativity of the generated networks vary across experimental configurations. More importantly, when comparing generated partisan exposure with the survey, some models generate stronger separation between Democratic and Republican egos than reported in the survey, with higher same-party and lower cross-party exposure, while others mainly underestimate Republican exposure across ego groups. Moreover, networks with similar political assortativity can still generate different partisan environments around the same personas, including among networks with plausible structural properties. Finally, generated networks show group-specific errors, under- or overestimating exposure to either Democrats or Republicans for specific social groups. These findings show that evaluating LLM-based social simulations only through aggregate outcomes can hide errors in the local environments through which those outcomes emerge, highlighting the importance of validation at both aggregate and individual levels.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23199
PDF
-
QuAD: Quantitative Assessment via Distribution-Alignment for Qualitative Data Quality Enabled by a Content-Aware Multi-Agent System
2026-10-16 08:46:00Wenshuo Zhang, Leixian Shen, Qiqi Zhou, Shuchang Xu, Feiyang Hao, Huamin Qu, Haobo Li, Zhao Chen, Lin-Ping YuanAbstract
Assessing whether qualitative responses collected from semi-structured questions are ready for a particular analysis goal is a persistent challenge. Manual qualitative analysis is interpretive and labor-intensive, while existing automated methods often lack a dataset-level perspective for deciding whether a response set supports a researcher-selected analytical lens. We introduce QuAD, a framework for quantitative pre-analysis assessment of qualitative response datasets. QuAD compares a reconstructed intrinsic cluster distribution reconstructed from responses with an extrinsic, researcher-defined analytical lens derived from metadata. QuAD is structured into a four-quadrant assessment whose metrics are read jointly, from lens-level relations to within-cluster variation, to provide fitness-for-purpose signals for revealing general patterns and unique insights. Because this assessment relies on lens-conditioned inter-response dissimilarity, we propose a content-aware multi-agent system with two-stage instruction generation and adaptive anchors to improve scoring consistency. We validate QuAD through controlled experiments on synthetic data, including robustness and baseline comparisons, and a real-world social survey case study. The case study shows how QuAD quantitatively assesses whether a selected analysis axis is promising and also surfaces representative or unusual responses for human interpretation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23153
PDF
-
Path to Prior-Data Fitted Relational Models via Learned Latent Multi-table Representations
2026-10-16 07:43:20Mohammad Sadeq Abolhasani, Viswanath GanapathyAbstract
Prior-data fitted networks (PFNs) show that pretraining on large populations of synthetic tasks can enable generalization to unseen datasets with little or no downstream fine-tuning. This paradigm is effective for transformer-based tabular and relational foundation models such as RDB-PFN, but remains largely unexplored for graph-based relational models built on message passing. We pretrain the graph-based relational foundation model Griffin on large collections of synthetic relational databases and ask whether curriculum learning, which benefits transformer-based relational learners, also improves message-passing representations. Rather than fine-tune on downstream tasks, we use the pretrained encoder as a general-purpose relational representation learner and pass its latent representations to a frozen in-context predictor (\ticl{}); no component is trained on the target task. On 16 real-world relational classification tasks, evaluated over five seeds against raw-feature and untrained-encoder baselines, a purely synthetic curriculum that begins with schema-guided data and continues with schema-agnostic data gives the strongest frozen in-context performance\rev{, outperforming real-data-only pretraining and every unordered single-stage mixture of the corpora; when appended after real-data pretraining, it yields the best encoders overall}. These results provide initial evidence that PFN-style synthetic pretraining transfers to graph-based relational foundation models.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23073
PDF
-
Before Retrieval Begins: Safety and Tool-Use Decisions in LLM Agents
2026-10-16 07:42:47Aditya Nawal, Manit Baser, Mohan GurusamyAbstract
Large language models increasingly act as agents that call external tools, yet most tool-safety research examines only what follows a tool call. The prior decision of whether to call the tool remains largely unexamined and can influence downstream safety. Across the seven open-weight models, the unweighted model-average harm rate after admitted harmful requests is 74.5%. To identify what governs this decision, we apply a factorial intervention to the input request. Within our generated construction, neutralizing the requested-operation component produces the largest admission contrast (19 pp). A linear direction estimated from this contrast influences held-out admission in four of seven models; effects on operation-neutralized requests in some models show that it is not an operation-specific mechanism. We then test whether written refusal is behaviorally and representationally coupled to the same decision. Written refusal accompanies 33.6% of admitted harmful calls. Plain-text refusal training reduces unsafe admission in models that retain benign tool use, showing that response-level safety training can transfer to the call decision. Together, these results establish a partial, model-dependent relation between written refusal and tool admission. They motivate direct evaluation and supervision of tool admission rather than treating text refusal as its proxy.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23071
PDF
-
Known Music, Unknown Response: Leakage-Audited Dynamic Arousal Forecasting With Scheduled Future Music
2026-10-16 07:40:19Bin Wen, Dai-Qiao Zhang, Tien-Ping TanAbstract
Dynamic music emotion recognition usually estimates concurrent or lag-aligned labels from audio that has already been observed. We instead forecast the change in consensus arousal when the upcoming music is scheduled but all later affect labels remain hidden. Evaluation holds out complete songs, encodes each eligible 4-s chunk independently, predicts arousal innovation, and compares the correct future with displaced segments from the same song. On PMEmo and a 1,494-song DEAM evaluation pool excluded from engineering development, a complete past/future MuQ representation raises concordance correlation coefficient (CCC) by 0.389--0.507 over recent affect and remains 0.268--0.382 above a calibrated nonlinear state model. A future-only trajectory contains no past or current audio and still exceeds that state model by 0.150--0.249. The earliest legal future chunk, which ends 5.5--11 s before the target, also remains informative. Correct placement exceeds an overlapping 5-s shift by 0.100--0.209 and the acoustic-nearest eligible same-song segment by 0.078--0.105, with positive song-cluster lower bounds. These results show that both scheduled content and its within-song position carry forecast information under the stated observation rules. The study provides a leakage-controlled reference for known-future music forecasting without treating predictive substitutions as causal interventions.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23063
PDF
-
GR-VIP: Geometric representation conditioning for precise visuomotor policy
2026-10-16 06:21:43Chanhwi Lee, Jiwon Seong, Eunje Choi, Hohyung Lee, Jongsoo Lee, Junyeong Bae, Inveom Kwak, Woosang Shin, Soohee HanAbstract
Achieving precise terminal position and heading alignment remains a significant challenge for learning-based mobile robot control. Recent vision-based learning methods have shown promise for precise target-relative control and generalization to unseen environments with pretrained visual encoders, but general-purpose visual representations are not specifically designed to capture the fine-grained spatial differences between current and goal views required for precise control, and real-world demonstrations combining millimeter-scale terminal accuracy with zero-shot transfer across environments remain limited. To address these challenges, we propose Geometric Representation Conditioning for Precise Visuomotor Policy (GR-VIP), a goal-conditioned visuomotor policy that leverages a visual encoder pretrained for relative camera pose estimation. Rather than using the final relative-pose estimate, GR-VIP conditions action prediction on the dense relational features produced before pose regression, preserving fine-grained cross-view information for learning corrective actions from demonstrations. We evaluate GR-VIP on a real-world docking task and demonstrate high docking success rates and millimeter-scale terminal accuracy in both the training and unseen environments, without additional training for transfer. Furthermore, supplementary experiments illustrate the policy's ability to align with non-docking targets and complete docking under a tested low-light condition.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22997
PDF
-
NL2SQL with Iterative Self-Refinement
2026-10-16 05:39:18Anjali Vemula, Akshat DasulaAbstract
Bridging the gap between human intent and machine logic remains a critical challenge in data access for non-technical users, yet Large Language Models (LLMs) remain unreliable: they hallucinate schema elements, generate syntactically invalid queries, or fail to capture user intent. These limitations are especially critical in domains such as insurance, where KPIs, regulatory constraints, and legacy relational systems demand high precision. We introduce a multi-agent, persona-driven NL2SQL framework that combines (1) domain relevance detection, (2) schema-grounded knowledge construction, (3) KPI-aware SQL synthesis, (4) syntax-level self-repair using sqlite execution feedback, and (5) semantic consistency checking via SQL-to-NL reverse engineering. Our system significantly reduces query hallucination and improves semantic fidelity compared to direct LLM prompting. Evaluated on 60 queries (50 from a HuggingFace text-to-SQL dataset and 10 custom domain queries), the system achieves 90% correctness using Mistral across seven coordinated LLM calls showing that this approach can substantially increase the reliability of NL2SQL pipelines in high-stakes environments.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22968
PDF
-
Rethinking Magnitude Compression in Spectral Losses for DDSP Parameter Estimation
Abstract
Spectral losses for differentiable digital signal processing (DDSP) commonly compress magnitudes, for example by using log-magnitude terms. Such compression mimics human perception, but whether it helps the optimization is less clear, and is usually found only by comparing trained models. In this work, we show that whether compression helps depends on the system's informative region: the region of its dynamic range that carries the information pointing toward the target. To indicate where this region lies without having to train, we introduce concordance, which measures how well a loss orders candidate parameter settings by their distance from the target. We then compare uncompressed, compressed, and combined losses by fitting a modal plate reverb and a subtractive synthesizer model to target sounds. A third system, selected for its low-energy informative region, tests the relationship in the opposite direction. In every system, the loss that matches the informative region performs best: the uncompressed one where the region lies at high energies, and the compressed one where it lies low. Surprisingly, the common combination of both log-magnitude and linear-magnitude terms performs best in none of the systems. Code and audio examples are available at this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.22962
PDF
-
Recognizing Atari and Assessing Sente: Controlled Evaluation Tasks for Language-Based Go Agents
2026-10-16 05:23:01Taiyi Chen, Iskar Deng, Amandalynne PaulladaAbstract
Domain terminology provides concise descriptions of game states and strategic relationships, but whether game-playing language models can accurately recognize these concepts and relate them to move evaluation remains unclear. We construct a controlled evaluation set centered on atari and its relationship to sente in Go, examining terminology recognition under local board changes and move evaluation under different strategic conditions. We conduct our tests on LoGos, a Go language model, after fine-tuning it with terminology and commentary supervision. The model struggles to recognize changes in the atari relationship and assess its strategic implications. Its terminology predictions are associated with move preferences even when those preferences contradict the reference evaluation. Our controlled tests provide a framework for examining whether language-based Go agents connect domain terminology with precise board relationships and strategic move values.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22953
PDF
