Relation
-
Robot-WATCHDOG : failure detection through object-centric graph representation
2026-10-09 11:19:25Quentin Rolland, Fabrice Mayran de Chamisso, Jean-Baptiste MouretAbstract
Reliable real-time failure detection is critical for deploying learned robotic policies, yet defining failures explicitly is infeasible in open-world settings. This motivates failure detection from nominal demonstrations alone. Existing methods, however, struggle to balance robustness to benign variations with the ability to capture semantic and interaction-level errors. We introduce Robot-WATCHDOG, a self-supervised framework that models manipulation scenes as object-centric spatio-temporal graphs. Building on this representation, we investigate two complementary failure scores: Trajectory Projection and Correlation (TPC), a non-parametric measure of geometric deviation and relational consistency, and GnnT, a Graph Attention Network with a Transformer that predicts future object states. We evaluate both on a public benchmark and on a new dataset of semantically complex manipulation tasks, across six tasks and ten random seeds. Both scores outperform image-based failure detectors, particularly on semantic and interaction-level failures. TPC provides the strongest performance in AUPR and MCC on both dataset averages, with low variance across seeds. Qualitative results are made available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13403
PDF
-
Radiomics-Based Thyroid Nodule Classification with Label-Conditional Conformal Prediction
2026-10-09 11:01:07Laura Testa, Pierpaolo Brutti, Umberto Ferraro PetrilloAbstract
Thyroid nodule malignancy assessment relies on ultrasound imaging, yet current risk stratification systems suffer from substantial interobserver variability, contributing to a high rate of unnecessary biopsies. We propose a radiomics-based framework combining quantitative feature extraction via PyRadiomics with a Generalized Additive Model (GAM) classifier, selected among six candidates for its favorable trade-off between discriminative performance and interpretability. To complement point predictions with uncertainty estimates, Cross-Conformal Prediction with label-conditional guarantees is applied, flagging ambiguous cases for clinical review rather than forcing a binary decision. Experiments are conducted on TN5000, a publicly available ultrasound dataset of thyroid nodules. After Spearman correlation filtering, 36 features are retained and the GAM achieves an AUC of $0.89$, a sensitivity of $0.83$, and a specificity of $0.82$ on the validation set. At a significance level $\epsilon=0.09$, selected to ensure empirical coverage guarantees on both classes, 63\% of nodules on the test set receive a certain (i.e., single-label) prediction, with conditional precision of $0.94$ for certain malignant and conditional Negative Predictive Value (NPV) of $0.73$ for certain benign cases, while the remaining 37\% are referred to the clinician.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13387
PDF
-
Green-Routed Neural Operators: Physics Determines Where the Network Reads
Abstract
We identify a mismatch between the physical role of transport fields in many PDEs and their usual role in neural operators: PDEs use them to select read coordinates, whereas neural operators typically treat them only as input values. We address this mismatch with the Green-Routed Neural Operator (GRNO), which uses the governing equation to determine where latent features are sampled. A parameter-free equation adapter evaluates the diagnostic relation and constructs a departure map whose values are the read coordinates. A multiscale encoder-decoder combines centered and routed reads of latent features to learn the complete finite-time update. Across five two- and three-dimensional PDE systems, GRNO achieves the lowest mean final relative $L^2$ error on four under 40-step autoregressive evaluation and remains competitive on Keller-Segel. Fixed-weight route interventions reveal strong dependence on direction and spatial alignment in four systems, with weak dependence in Keller-Segel. In independently trained ablations, GRNO achieves lower mean errors than variants that supply the transport field only as an input feature, substitute a learned displacement for the equation-specified route, or apply the route with a spatial misalignment, across all five systems. It also substantially outperforms directly advecting the physical state and learning the remaining update, indicating that equation-specified read coordinates provide an effective structural prior for long-horizon PDE forecasting.
Abstract (translated)
URL
https://arxiv.org/abs/2610.05337
PDF
-
Host-Aware Web Crawling for LLM Pretraining Data
Abstract
Web crawling is a major source of large language model (LLM) pretraining data, yet data-selection pipelines discard a large share of crawled pages. We investigate how a crawler should allocate its budget across and within hosts to collect more high-quality pretraining data. Combining document-level quality classifier scores, web-graph centrality metrics, and Common Crawl's per-host crawl coverage, we find that roughly half of the variation in classifier scores occurs between hosts. In the crawls we analyze, a few pages from a host also provide a useful estimate of the quality of its remaining pages. Common Crawl uses harmonic centrality, a graph centrality metric, to guide its crawl allocation. In our simulations, using centrality to choose which hosts to crawl yields limited gains over random ordering and performs worse for some classifiers. For deciding how deeply to crawl each host, sampling a few pages and then fetching more from hosts with higher-scoring samples collects several times more high-quality pages per fetch than uniform depth or centrality-based allocation. Finally, Common Crawl's observed per-host coverage has little correlation with the evaluated quality signals. We estimate that tens of millions of high-quality pages remain among known but uncrawled URLs in each crawl examined, with most concentrated on a small share of hosts.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13321
PDF
-
SheafPrune: Sheaf-Guided Graph Propagation for Visual Token Pruning
2026-10-09 09:15:08Xiaoyang Ma, Chi Wang, Hong SunAbstract
Multimodal large language models process the complete visual token sequence, increasing prefill cost even when many tokens are irrelevant to the instruction. Token-wise saliency captures limited inter-token dependence; graph-based selection instead depends on how relations govern importance propagation and ranking. We study support-constrained propagation with node-degree correction. Inspired by sheaf geometry, SheafPrune uses modality-specific maps and a sparse text--visual graph to transfer relevance, then propagates scores on a separate visual graph and corrects them for degree. It retains a hard top-$k$ subset once before the frozen language model. The selector has about $4.5$M parameters and is trained end-to-end through the frozen LLaVA-NeXT-8B backbone using only the language-modeling objective. Explicit retention-ratio conditioning lets one checkpoint serve every budget. Across four backbones, ten benchmarks and seven pruning ratios, with all baselines re-implemented under one protocol, SheafPrune achieves the best retention at $22$ of $28$ backbone--budget settings, with monotonically growing margins in the moderate-to-aggressive regime. On LLaVA-NeXT, retaining $10\%$ of visual tokens yields a $5.15\times$ net prefill speedup and an $84.0\%$ end-to-end FLOPs reduction. Together with component ablations, these results support graph-constrained importance propagation and degree correction as a design for visual token selection across the evaluated backbones and tokenization schemes, improving the trade-off between accuracy retention and inference cost. code:this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.13263
PDF
-
Beyond a Single Crop: Contextualized Embeddings for Player Re-Identification
2026-10-09 09:07:45Ge Luo, Changhuo Yang, Weisi Fan, Rui Yang, Shaokai WangAbstract
Person re-identification is typically addressed by learning identity-discriminative embeddings from individual person crops. However, player re-identification in broadcast sports videos presents a unique challenge: players from the same team often share similar appearances, while video sequences provide repeated observations of the same players under different viewpoints and surrounding contexts. Existing crop-based approaches largely ignore this contextual information, which can be critical for resolving visually similar identities. Here, we propose ContextReID, a contextualized embedding framework that represents a player by jointly considering other players in the same frame and observations from different frames of the broadcast sequence. By incorporating both co-occurring players and cross-frame observations, the model learns identity features relative to the surrounding visual context rather than relying only on isolated appearance cues. We implement this framework with a vision-language model that takes sets of player crops as input and generates context-aware embeddings for individual players. A combined contextual learning and retrieval objective encourages the model to capture cross-frame identity relationships while maintaining discriminative embeddings for player matching. Experiments across three multi-object tracking benchmarks show that ContextReID improves player retrieval over conventional single-crop embedding approaches in both Rank-1 and mAP. These results highlight the utility of spatial and temporal context for reliable player identification in broadcast sports videos.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13259
PDF
-
What Do Audio-Language Judges of Generated Music Listen For? Four Probes with Controls from Expert Ratings
2026-10-09 08:56:54Mateusz Modrzejewski, Tomasz RadzikowskiAbstract
Open audio-language models are used as judges of generated music: given a clip and its text prompt, the model rates the clip, and the judge is validated by how well its ratings correlate with expert ratings. The correlation does not show what the judge responds to: the music, the text prompt, or the way the question is asked. We propose four probes that test each of these, three of them read against a control computed from the human ratings: removing the audio, replacing the clip with another model's clip for the same prompt, swapping the order of two clips in pairwise judging, and rewording the instruction. We apply them to five open judges on all 2,748 clips of MusicEval, and the last two to the SongEval songs. Without audio, no judge exceeds what the prompt alone predicts from the human ratings, and for prompt alignment every judge falls below it. With audio, every judge follows the clip it hears when rating prompt alignment, two do when rating musical quality, and the strongest judge's quality score tracks the experts' alignment rating more than their quality rating. The pairwise verdicts of the four smaller judges follow the position of a clip in the pair (its slot) rather than its quality on both rating sets. For musical quality, rewording the instruction moves the correlation of most judges as much as changing the judge. MusicEval's prompt assignment bounds any prompt-only judge at the model level. We recommend reporting the four probes with every music judge.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13247
PDF
-
How Reliable are AMR Parser Outputs? Uncertainty Estimation for AMR Parsing
2026-10-09 08:53:02Anuj Kumar, Shintaro Ozaki, Yamuna Prasad, Katsuhiko Hayashi, Hidetaka Kamigaito, Taro WatanabeAbstract
Recent advances have significantly improved the performance of Abstract Meaning Representation (AMR) parsers, yet determining when their outputs can be trusted remains largely unexplored. This work presents the first study of uncertainty estimation for AMR parsers in a black-box setting using top-k beam-search candidates. Uncertainty is estimated from pairwise candidate similarities and evaluated using the Prediction Rejection Ratio. This work characterises the relationship between parsing performance and uncertainty, evaluates the reliability of beam candidate distributions, analyses the effect of evaluation metrics on uncertainty assessment, and identifies parsers that provide the strongest balance between performance and reliability. Experimental results show the value of uncertainty estimation as a complementary dimension for evaluating AMR parsers.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13236
PDF
-
Destination-Conditioned Adaptation with Semantic-Geometric Alignment for Generative Inbetweening
2026-10-09 08:10:13Zhiyu Xu (Tianjin University), Wei Shang (Singapore Management University), Yushen Xu (Tianjin University), Wenwen Li (Tianjin Medical University), Zhiyan Xu (Southeast University), Pengfei Zhu (Tianjin University), Dongwei Ren (Tianjin University)Abstract
Generative inbetweening aims to synthesize temporally coherent intermediate frames between a start frame and a target frame. Although pretrained image-to-video diffusion models provide strong priors for large-motion inbetweening, they are not explicitly designed to reach a specified target frame. They may therefore generate realistic individual frames while drifting from the target or producing unstable motion under large displacements and non-rigid dynamics. We propose DSG-GI, a framework that adapts pretrained latent video diffusion models through \textbf{D}estination-Conditioned Adaptation and \textbf{S}emantic-\textbf{G}eometric Alignment. Destination-Conditioned Adaptation treats the target frame as the destination of the sequence and provides temporally progressive guidance along the generated trajectory. Semantic-Geometric Alignment aligns the token-wise spatio-temporal relational geometry of backbone features with that of a frozen video foundation encoder and applies a flow-matching-aware latent flow constraint to samples near the data endpoint of the probability path. Together, these components strengthen destination guidance and preserve coherent semantic-geometric motion structure. Extensive experiments on standard and large-motion inbetweening benchmarks demonstrate improvements in temporal stability, target-frame faithfulness, and perceptual quality. Our code will be made publicly available.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13187
PDF
-
From Benchmark to Bench: Can Agents Survive Real-World Drug Discovery?
2026-10-09 08:05:52Pierre Llompart, Levent Guner, Helen Lai, Alessandro Tibo, Yijie XuAbstract
Agentic systems increasingly coordinate molecular-design tools, but it is unclear which layer of the stack limits outcomes on real projects. We developed MAGI, an open modular agent that authors objectives, launches and monitors optimization, interprets structure--activity relationships, and revises its strategy accordingly. MAGI generates molecules either directly through the LLM or by delegating to REINVENT 4, with scoring services interchangeable behind a common contract. We tested it across nine retrospective lead-optimization campaigns from three pharmaceutical companies, replayed under fixed temporal cutoffs. Both routes produced valid structures: LLM proposals stayed closer to local chemistry and reached comparable or higher primary activity in fewer operations, whereas REINVENT explored broader chemical space. Whether a campaign met its objective depended on the predictive models, not on the generation route: attainment followed model accuracy on the chemistry proposed, dropping once that chemistry moved outside the model's applicability domain. Separately, a blinded evaluation asked whether the MAGI's output could pass as expert work: chemists were not able to discriminate agentic proposals from held-out compounds, and judged the SAR reasoning broadly plausible yet incomplete. Together, these results position MAGI as a coordination layer pluggable into existing computational chemistry workflows. The ceiling on real projects, however, remains currently set by scorer applicability rather than by tool orchestration.
Abstract (translated)
URL
https://arxiv.org/abs/2610.06411
PDF
-
The Silent Failures in Agentic Data Science
2026-10-09 08:05:09Xue Li, Hongqian Xia, Daniel Gomm, A\'ecio Santos, Cornelius Wolff, Madelon HulsebosAbstract
Large language models have significantly lowered the barrier to writing code. Naturally, this has also led to the development of data science agents that promise automating the design and execution of data science from task formulation to model development. Existing evaluations of agentic data science (agentic DS) assess downstream predictive performance and code correctness, providing preliminary insight in agentic DS capabilities. We argue that these evaluations overlook the fundamental principles of data science: methodological data science- and domain knowledge. As such, only assessing downstream performance masks methodological failures such as data leakage and inappropriate validation, limiting the development of robust agentic DS systems. In this paper, we evaluate agentic DS beyond accuracy from three different angles: 1) a large-scale analysis of failure modes in common agentic DS frameworks and models across 220 data science tasks, 2) a reusable and extensible test suite with curated data science tasks that test for six specific failures in a controlled manner, and 3) a qualitative assessment of agentic DS pipelines against expert solutions on Kaggle competitions. We find that the majority of agentic solutions contain at least one failure mode despite the complexity of agentic harness or model capacity. Moreover, we identify a positive correlation between the occurrence of data leakage failures and predictive performance, confirming the necessity to evaluate agents beyond accuracy. Our qualitative analysis shows that DS agents generally lack problem solving creativity and domain knowledge, compared to competition-winning data scientists. We believe that principled failure mode analysis, as presented here, should be integral part of agentic DS evaluations, and that the insights we surface will be key in developing trustworthy agentic DS pipelines.
Abstract (translated)
URL
https://arxiv.org/abs/2610.14115
PDF
-
Les Mis'erables Dialogue: A film-based network representation of social communication
2026-10-09 07:38:15Theodora Moldovan, Georgios Panayiotou, Davide VegaAbstract
In this work, we revisit the classic Les Misérables benchmark network from the perspective of social communication. Using the 1998 film adaptation of the novel, we construct the publicly available Les Misérables Dialogue temporal text network, which explicitly distinguishes speakers, addressees, and other recipients of each utterance, along with its content and timing. Using the ten social dimensions model, we also derive multilayer network representations of the network, in which layers correspond to distinct relational dimensions. Beyond the network dataset, this work offers a general methodology for building similarly rich communication datasets from similar narrative sources.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13148
PDF
-
VIGOR: Verifiable Industrial Geometry Optimization and Repair in Scene Programs
2026-10-09 07:34:19Fuqiang Wang, Zheng Guo, Xiaoming Wu, Hanlin Kong, Nayu Liu, Chuanting Zhang, Daojun Liang, Jingxuan WeiAbstract
Large language models (LLMs) increasingly generate structured layouts and executable scene programs from natural-language instructions. However, executability does not imply engineering feasibility: an industrial scene program may execute successfully while its final state still violates coupled boundary, collision, clearance, aisle, or structural constraints. We identify this mismatch as the executability-engineering-feasibility gap, where locally plausible placements can remain globally infeasible because corrections to one device may introduce violations elsewhere. To make this gap measurable in a controlled setting, we construct an execution-grounded industrial scene-program dataset with 1,749 constructible scenarios, complete executable programs, and 94 final-state geometric checks per scenario. We further propose VIGOR, which combines supervised scene-program generation with execution-grounded verification and staged geometric refinement. Supervised fine-tuning establishes complete program generation, local projection resolves independently correctable violations, and joint conflict-graph repair coordinates residual multi-object conflicts while preserving structural relations. Experiments show that VIGOR achieves 96.86% Complete Feasibility and an Overall score of 91.20, outperforming the strongest evaluated baseline by 10.42 points in Overall. These results show that, under controlled industrial layout conditions, reliable scene-program generation requires not only executable programs, but also explicit verification and coordinated resolution of coupled engineering constraints.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13145
PDF
-
GuidedNav: Shaping Vision-Language Navigation Representations through Pre-action Attention and Spatial Guidance
2026-10-09 07:18:03Jingyu Guo, Jiaxin Huang, Chengxing Lin, Xiaoyu Luo, Cheng Wen, Shanshan Ye, Tingjin Chu, Shaoli Huang, Mingming GongAbstract
Vision-and-language navigation (VLN) requires an agent to track progress through an extended instruction, identify landmarks relevant to its current objective, and understand the surrounding spatial structure to act. End-to-end navigation policies typically rely on action supervision to implicitly learn these capabilities. Without explicit guidance on the evidence underlying each decision, however, policies can overfit to correlations predictive of training actions rather than learn the task-relevant grounding and geometry needed for generalization. Our insight is to guide the representations that connect instructions to actions: identifying what remains to be done determines which visual evidence matters, while understanding the geometry around that evidence informs how to move. We introduce GuidedNav, a unified framework that explicitly shapes these representations through training-time guidance. Subtask and landmark guidance steer native pre-action attention toward the active instruction segment and relevant visual regions, grounding action prediction in the current objective. Spatial guidance aligns the policy's internal representations with geometric features that capture long-horizon context and local spatial structure. Together, these objectives strengthen navigation capabilities while avoiding the inference overhead of intermediate textual reasoning and online geometric encoding. We also introduce Guided-R2R and Guided-RxR, two annotation-enriched navigation datasets that support more interpretable VLN research. GuidedNav establishes state-of-the-art performance among the compared monocular RGB policies, improving success rates by 8.1% and 13.1% relative to the strongest prior results on R2R-CE and RxR-CE val-unseen, respectively, while achieving faster inference. Extensive experiments further demonstrate the effectiveness and real-world transferability of our approach.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13122
PDF
-
BenCoDiC: A Large-Scale Contextual Cyberbullying Corpus for Bengali Political News Discourse FULL VERSION
2026-10-09 07:16:29Md. Nesarul Hoque, Rudra Pratap Deb Nath, Umme Salma, Shima Chakraborty, Md. Hanif SeddiquiAbstract
Cyberbullying is a growing concern in online communities, yet existing Bengali corpora remain limited in contextual information, annotation transparency, scale, accessibility, and support for multidimensional analysis, thereby hindering robust detection and comprehensive study of harasser behaviors and networks. To address these gaps, we introduce the Bengali Contextual and Diverse Cyberbullying (\textit{BenCoDiC}) corpus, a publicly available contextual cyberbullying resource for Bengali political news discourse comprising 50,250 textual instances collected from 100 YouTube videos and their associated discussions. The corpus preserves caption--comment--reply relationships and is organized through a nine-dimensional star schema covering users, videos, textual content, context, time, engagement, political parties, target identities, and language categories. Five AI chatbots were initially evaluated for annotation but did not meet the predefined reliability criterion. Consequently, a two-tier human annotation process with expert verification was adopted, achieving Fleiss' $\kappa=0.86$ and Krippendorff's $\alpha=0.86$. Statistical analyses characterize the corpus, while transformer-based experiments show that incorporating conversational context yields modest but consistent improvements over isolated-text classification. \textit{BenCoDiC} supports context-aware cyberbullying detection and perpetrator-oriented behavioral and network analysis. The corpus is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13121
PDF
-
Evo$^2$: Evolving the Evolver through Weight-Harness Co-Evolution
2026-10-09 05:28:02Chejian Xu, Shujian Zhang, Wenxuan Zhou, John Lambert, Beck Chen, Bo Li, Andrew Hard, Rajiv MathewsAbstract
Self-evolving agents are increasingly used to improve language model systems without human intervention through either weight updates or harness improvements. Existing approaches typically pursue these directions separately: some methods update model weights using self-generated experience, while others rewrite the harness that defines how an agent uses prompts, tools, context, and execution feedback. However, these approaches overlook the relationship between model weights and the agent harness. To connect these processes and ensure effective and smooth agent self-evolving, we propose Evo$^2$, a framework for weight-harness co-evolution. For harness updates, we design a unified dual-role pipeline that a single policy serves as both a Proposer, which writes harness edits, and a Reflector, which diagnoses their effects and guides revision. For weight updates, harness modifications and their execution outcomes guide the training of both the Proposer and the Reflector. We further develop EvoTIDE, a training pipeline that recovers usable trajectories through edit extraction and prefix continuation, then combines SFT with interleaved GRPO across the two roles. Extensive experiments across three coding benchmarks demonstrate that Evo$^2$ significantly outperforms existing self-evolution methods. It achieves 82.1% on Polyglot and 48.3% on SWE-bench Verified, compared with 62.6% and 41.0% for the strongest baseline, respectively. We also show that the evolved harnesses transfer to different tasks without further evolution and rank first in cross-benchmark evaluations. Our dual-role harness improvement framework is also able to extend to self-evolution with proprietary models, improving a GPT-5-mini agent's performance from 24.4% to 48.3%. These results demonstrate the applicability of the framework Evo$^2$ across domains and its broad transferability across models and tasks.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13025
PDF
-
Learning Features, Not Layouts: Feature-Axis Attention as a Transfer Prior for Medical Imaging
2026-10-09 05:16:26Aon Safdar, Mohamed SaadeldinAbstract
Natural-image-pretrained foundation models are increasingly adapted to medical imaging, yet transfer remains unreliable under domain shift, modality heterogeneity, and label scarcity. We trace part of this fragility to an overlooked design choice. Standard vision transformers place all global modeling on self-attention over spatial tokens, an object-layout prior well suited to natural scenes but not to medical images, where the discriminative signal lies in feature correlations and texture that recur across scanners while layout does not. We ask whether the axis of global attention, spatial versus feature, is itself a lever for transferable medical representations. Existing channel-aware hybrids confound this question, adding channel attention to a spatially-mixed backbone and leaving the axes coupled and the feature axis unmeasurable in isolation. We design FAD-ViT, a backbone that strictly decouples the two axes, making feature-axis attention the primary global operator and the attention axis a controlled variable. Evaluating comprehensively across 23 classification, segmentation, and low-data tasks under matched tokenization, capacity, and protocol, we find that shifting global attention from the spatial to the feature axis leaves from-scratch performance essentially unchanged, yet markedly strengthens transfer. Identical ImageNet pretraining yields up to roughly three times the transfer gain, with consistent improvements on every held-out segmentation task at up to a quarter the parameter count and far lower compute than standard and channel-attention baselines. The advantage is largest where texture rather than geometry is discriminative, tracking greater reuse of pretrained features. The axis of global attention is thus a design lever for medical transfer, and making it channel-primary is a simple, cheap, and principled choice.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13012
PDF
-
Provenance-Aware Belief Updating in Human-AI Feedback Loops
2026-10-09 05:09:01Tianyi Huang, Eric Liu, Jay Chong, Emily Yin, Wanqi ZhaoAbstract
In repeated human-AI interaction, a single observation can be quoted, summarized, and returned to a model as multiple reports, making repetition look like independent corroboration. We study whether language models can use supplied report lineage to update according to evidence provenance rather than report count. We introduce Latent Quotient Evidence Training (LQET), a relational objective that combines sparse Bayesian supervision with constraints that encourage stable predictions when reports add no new evidence and consistent updates to the same new evidence across relay histories. On a controlled binary benchmark, LQET reduces new-evidence update RMSE by 41-44% and log-odds drift after eight relay steps by 89-91% relative to task-only training across Qwen3-4B and Phi-4-mini, with three paired training seeds per backbone. The gains extend to a closed-loop simulation in which model confidence controls how many relayed reports re-enter the model's context in later rounds. By grounding belief updates in supplied provenance, LQET offers a route toward dynamic human-AI systems in which influence follows new evidence, not the number of times the same evidence returns.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13008
PDF
-
Language Models Have Interpretable Narrative Mechanisms
2026-10-09 04:45:52David Yiyang Liu, Aditya Joshi, Paul Dawson, Andrew PiperAbstract
We investigate whether language models contain internal components that contribute to representing narrativity, the degree to which a text exhibits narrative properties. Across GPT-2-Small, Gemma-2-2B, and Llama-3.1-8B, we identify attention heads, MLP neurons, and sparse autoencoder features whose activations correlate with narrativity. Ablating selected neuron and feature sets increases next-token prediction loss more for high-narrativity than for low-narrativity texts, and reduces the narrativity of open-ended generations. On downstream benchmarks, the largest effects occur in story completion and narrative question answering, although they vary across models and languages; results on confabulation and hallucination benchmarks are mixed. These findings provide causal evidence that selected sets of narrative-associated components contribute to model behaviour, while their internal organisation, relation to narrative theory, and broader functions remain open questions.
Abstract (translated)
URL
https://arxiv.org/abs/2610.12989
PDF
-
Forecasting Corpus-Sampling Disagreement in Masked Text Reconstruction
2026-10-09 04:40:47Hare KrishnaAbstract
If a second text corpus were collected from the same population, how much would a predictor's outputs change? We study this question for masked-text reconstruction using a smoothed predictor built from nearby token-pair counts and evaluated over the full 50,257-token GPT-2 vocabulary. Treating each source document as one observation, we derive a first-order formula for the expected disagreement between predictors fitted to two independent corpora. The formula accounts for variable document length, random context counts, and correlations across token offsets, and it can be evaluated from a separate reference corpus without access to either target corpus. On TinyStories, WikiText-103, and CNN/DailyMail, growing each corpus from 512 to 2,048 chunks of 64 tokens lowers disagreement by only 5--40\%, far short of the 75\% implied by $1/n$ scaling. The forecast tracks this slow decline, which we trace to smoothing of rarely seen contexts. Forecast accuracy depends less on how these correlations are modeled than on the size of the reference corpus: small references systematically underpredict disagreement. A source-split jackknife that uses only reference data reduces this calibration error by 57--59\%. After this correction, a simpler smoothed-multinomial approximation is most accurate when the reference corpus is smaller than the target corpus, and a nonlinear source bootstrap is most accurate when it is larger. Finally, small masked diffusion language models trained on the same corpora show that the count-based forecasts partly identify which inputs are most sensitive to the corpus, but miss the neural models' much faster decline in disagreement.
Abstract (translated)
URL
https://arxiv.org/abs/2610.12987
PDF
