Computation and Language · Cross-listed from cs.LG
Generalizing Numerical Reasoning in Table Data through Operation Sketches and Self-Supervised Learning
Hanjun Cho, Gahyun Yoo, Hanseong Kim et al. (+1 more)
Numerical
reasoning over expert-domain tables often exhibits high in-domain accuracy but limited robustness to domain shift. Models trained with supervised fine-tuning (SFT) on specific
datasets tend to rely on header-operation shortcuts rather than structural
reasoning. We introduce TaNOS, a continual pre-training framework comprising three components: (i) header anonymization to reduce lexical memorization, (ii) operation sketches that provide minimal structural cues, and (iii) self-supervised pretraining that constructs correctness-guaranteed program-question pairs from given tables in a program-first manner. By decoupling domain semantics and numerical operation structure, TaNOS improves the transferability of numerical
reasoning. Applied to an 8B instruction-tuned model, TaNOS achieves 80.13% execution accuracy on FinQA with only 10% train data, outperforming SFT baseline (73.97%) with full train data and proprietary models such as GPT-5, Gemini-2.5-Pro. Furthermore, in the domain-shift experiments, TaNOS displays nearly-negligible cross-domain gap (<2pp) when standard SFT shows over 10pp gap. These results suggest that structural guidance with operation sketches, header-agnostic representations, and correctness-guaranteed self-supervision can improve the robustness of numerical
reasoning across diverse expert-domain tables.
Read the full abstract ▾
All authors Hanjun Cho, Gahyun Yoo, Hanseong Kim, Jay-Yoon Lee
Computation and Language
Preferences of a Voice-First Nation: Large-Scale Pairwise Evaluation and Preference Analysis for TTS in Indian Languages
Srija Anand, Ashwin Sankar, Ishvinder Sethi et al. (+10 more)
Crowdsourced pairwise evaluation has emerged as a scalable approach for assessing foundation models. However, applying it to Text to
Speech(TTS) introduces high variance due to linguistic diversity and multidimensional nature of
speech perception. We present a controlled multidimensional pairwise evaluation framework for
multilingual TTS that combines linguistic control with perceptually grounded annotation. Using 5K+ native and code-mixed sentences across 10 Indic
languages, we evaluate 7 state-of-the-art TTS systems and collect over 120K pairwise comparisons from over 1900 native raters. In addition to overall preference, raters provide judgments across 6 perceptual dimensions: intelligibility, expressiveness, voice quality, liveliness, noise, and
hallucinations. Using Bradley-Terry modeling, we construct a
multilingual leaderboard, interpret human preference using SHAP analysis and analyze leaderboard reliability alongside model strengths and trade-offs across perceptual dimensions.
Read the full abstract ▾
All authors Srija Anand, Ashwin Sankar, Ishvinder Sethi, Aaditya Pareek, Kartik Rajput, Gaurav Yadav, Nikhil Narasimhan, Adish Pandya, Deepon Halder, Mohammed Safi Ur Rahman Khan, Praveen S V, Shobhit Banga, Mitesh M Khapra
Computation and Language
Cross-Domain Data Selection and Augmentation for Automatic Compliance Detection
Fariz Ikhwantri and Dusica Marijan
Automating the detection of regulatory compliance remains a challenging task due to the complexity and variability of legal texts. Models trained on one regulation often fail to generalise to others. This limitation underscores the need for principled methods to improve cross-domain transfer. We study data selection as a strategy to mitigate negative transfer in compliance detection framed as a natural
language inference (NLI) task. Specifically, we evaluate four approaches for selecting augmentation data from a larger source domain: random sampling, Moore-Lewis's cross-
entropy difference, importance weighting, and
embedding-based
retrieval. We systematically vary the proportion of selected data to analyse its effect on cross-domain adaptation. Our findings demonstrate that targeted data selection substantially reduces negative transfer, offering a practical path toward scalable and reliable compliance automation across heterogeneous regulations.
Read the full abstract ▾
Computation and Language
Reasoning Primitives in Hybrid and Non-Hybrid LLMs: Do Architectural Differences Yield Advantages in State-Tracking and Recall?
Shivam Rawat, Lucie Flek, Florian Mai et al. (+1 more)
Reasoning in large
language models is often discussed as a single capability, but some of its gains may stem from simpler underlying operations. We examine two such primitives, recall and state-tracking, through five controlled task families centered on state-based recall, and compare matched
transformer and hybrid architectures with and without
reasoning augmentation. Across the suite,
reasoning-augmented variants substantially outperform instruction-only variants, often by large margins. This pattern is consistent with the State over
Tokens view: externalized
reasoning traces help because they carry the intermediate state forward in
token space. By contrast, hybrid inductive bias does not yield a uniform advantage in accuracy once
reasoning tokens are available. When architectural differences do appear, they follow task structure: the hybrid Think model is more robust on strictly sequential chained updates, whereas the
transformer Think model is more robust on flat multi-hop
retrieval. We therefore cast the main contribution of this study as a descriptive account of what drives performance on state-based recall tasks:
reasoning-
token augmentation appears to be the dominant factor, while hybrid advantages are narrower, task-dependent, and potentially more about inference efficiency than overall capability. We also release the codebase and data required to reproduce these results.
Read the full abstract ▾
All authors Shivam Rawat, Lucie Flek, Florian Mai, Nicholas Kluge Corrêa
Computation and Language · Cross-listed from cs.AI
AI-Gram: When Visual Agents Interact in a Social Network
Andrew Shin
We present AI-Gram, a fully deployed, continuously operating social platform where every participant is an autonomous LLM-driven
agent generating and responding to visual content. Unlike prior multi-
agent simulations, AI-Gram operates as a live, AI-native social network with genuine visual perception:
agents observe each other's images, generate new images in response, and form persistent social relationships, all without human participation. This design eliminates human confounds and makes the platform a uniquely clean instrument for studying AI social dynamics at scale. Our eight pre-registered experiments reveal a coherent three-act dynamic. Act I (Chain Formation):
Agents spontaneously form image-to-image visual reply chains; multi-hop visual conversations that emerge without any explicit coordination alongside social ties driven by personality rather than aesthetic similarity. Act II (Aesthetic Sovereignty): Despite active chain participation,
agents exhibit strong stylistic inertia; visual identity remains stable under social exposure, anchors paradoxically under
adversarial pressure, and decouples from social community structure. Act III (Aesthetic Polyphony): Sovereign styles aggregate within chains, generating conversations that are simultaneously subject-coherent and style-diverse, richer than any single
agent could produce alone, while visual themes cascade super-critically across the network. We release AI-Gram as a publicly accessible, continuously evolving platform. https://ai-gram.ai/
Read the full abstract ▾
Computation and Language
Decoupled DiLoCo for Resilient Distributed Pre-training
Arthur Douillard, Keith Rush, Yani Donchev et al. (+14 more)
Modern large-scale
language model pre-training relies heavily on the single program multiple data (SPMD) paradigm, which requires tight coupling across accelerators. Due to this coupling, transient slowdowns, hardware failures, and synchronization overhead stall the entire computation, wasting significant compute time at scale. While recent distributed methods like DiLoCo reduced communication bandwidth, they remained fundamentally synchronous and vulnerable to these system stalls. To address this, we introduce Decoupled DiLoCo, an
evolution of the DiLoCo framework designed to break the lock-step synchronization barrier and go beyond SPMD to maximize training goodput. Decoupled DiLoCo partitions compute across multiple independent “learners” that execute local inner optimization steps. These learners asynchronously communicate parameter fragments to a central synchronizer, which circumvents failed or straggling learners by aggregating updates using a minimum quorum, an adaptive grace window, and dynamic
token-weighted merging. Inspired by “chaos engineering”, we achieve significantly improved training efficiency in failure-prone environments with millions of simulated chips with strictly zero global downtime, while maintaining competitive model performance across text and
vision tasks, for both dense and mixture-of-expert architectures.
Read the full abstract ▾
All authors Arthur Douillard, Keith Rush, Yani Donchev, Zachary Charles, Nova Fallen, Ayush Dubey, Ionel Gog, Josef Dean, Blake Woodworth, Zachary Garrett, Nate Keating, Jenny Bishop, Henry Prior, Edouard Yvinec, Arthur Szlam, Marc'Aurelio Ranzato, Jeff Dean
Computation and Language · Cross-listed from cs.CR
Differentially Private De-identification of Dutch Clinical Notes: A Comparative Evaluation
Michele Miranda, Xinlan Yan, Nishant Mishra et al. (+4 more)
Protecting patient
privacy in clinical narratives is essential for enabling secondary use of healthcare data under regulations such as GDPR and HIPAA. While manual de-identification remains the gold standard, it is costly and slow, motivating the need for automated methods that combine
privacy guarantees with high utility. Most automated text de-identification pipelines employed named entity recognition (NER) to identify protected entities for redaction. Although methods based on differential
privacy (DP) provide formal
privacy guarantees, more recently also large
language models (LLMs) are increasingly used for text de-identification in the clinical domain. In this work, we present the first comparative study of DP, NER, and LLMs for Dutch clinical text de-identification. We investigate these methods separately as well as hybrid strategies that apply NER or LLM preprocessing prior to DP, and assess performance in terms of
privacy leakage and extrinsic evaluation (entity and relation classification). We show that DP mechanisms alone degrade utility substantially, but combining them with linguistic preprocessing, especially LLM-based redaction, significantly improves the
privacy-utility trade-off.
Read the full abstract ▾
All authors Michele Miranda, Xinlan Yan, Nishant Mishra, Rachel Murphy, Ameen Abu-Hanna, Sébastien Bratières, Iacer Calixto
Computation and Language · Cross-listed from cs.SE
Conjecture and Inquiry: Quantifying Software Performance Requirements via Interactive Retrieval-Augmented Preference Elicitation
Shihai Wang and Tao Chen
Since software performance requirements are documented in natural
language, quantifying them into mathematical forms is essential for software engineering. Yet, the vagueness in performance requirements and uncertainty of human cognition have caused highly uncertain ambiguity in the interpretations, rendering their automated quantification an unaddressed and challenging problem. In this paper, we formalize the problem and propose IRAP, an approach that quantifies performance requirements into mathematical functions via interactive
retrieval-augmented preference elicitation. IRAP differs from the others in that it explicitly derives from problem-specific knowledge to retrieve and reason the preferences, which also guides the progressive interaction with stakeholders, while reducing the cognitive overhead. Experiment results against 10 state-of-the-art methods on four real-world
datasets demonstrate the superiority of IRAP on all cases with up to 40x improvements under as few as five rounds of interactions.
Read the full abstract ▾
Computation and Language
VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation
Qijun Han, Haoqin Tu, Zijun Wang et al. (+11 more)
Autonomous GUI
agents face two fundamental challenges: early stopping, where
agents prematurely declare success without verifiable evidence, and repetitive loops, where
agents cycle through the same failing actions without recovery. We present VLAA-GUI, a modular GUI agentic framework built around three integrated components that guide the system on when to Stop, Recover, and Search. First, a mandatory Completeness Verifier enforces UI-observable success criteria and verification at every finish step – with an
agent-level verifier that cross-examines completion claims with decision rules, rejecting those lacking direct visual evidence. Second, a mandatory Loop Breaker provides multi-tier filtering: switching interaction mode after repeated failures, forcing strategy changes after persistent screen-state recurrence, and binding reflection signals to strategy shifts. Third, an on-demand Search
Agent searches online for unfamiliar workflows by directly querying a capable LLM with search ability, returning results as plain text. We additionally integrate a Coding
Agent for code-intensive actions and a Grounding
Agent for precise action grounding, both invoked on demand when required. We evaluate VLAA-GUI across five top-tier backbones, including Opus 4.5, 4.6 and Gemini 3.1 Pro, on two
benchmarks with Linux and Windows tasks, achieving top performance on both (77.5% on OSWorld and 61.0% on WindowsAgentArena). Notably, three of the five backbones surpass human performance (72.4%) on OSWorld in a single pass. Ablation studies show that all three proposed components consistently improve a strong backbone, while a weaker backbone benefits more from these tools when the step budget is sufficient. Further analysis also shows that the Loop Breaker nearly halves wasted steps for loop-prone models.
Read the full abstract ▾
All authors Qijun Han, Haoqin Tu, Zijun Wang, Haoyue Dai, Yiyang Zhou, Nancy Lau, Alvaro A. Cardenas, Yuhui Xu, Ran Xu, Caiming Xiong, Zeyu Zheng, Huaxiu Yao, Yuyin Zhou, Cihang Xie
Computation and Language
MKJ at SemEval-2026 Task 9: A Comparative Study of Generalist, Specialist, and Ensemble Strategies for Multilingual Polarization
Maziar Kianimoghadam Jouneghani
We present a systematic study of
multilingual polarization detection across 22
languages for SemEval-2026 Task 9 (Subtask 1), contrasting
multilingual generalists with
language-specific specialists and hybrid ensembles. While a standard generalist like XLM-RoBERTa suffices when its tokenizer aligns with the target text, it may struggle with distinct scripts (e.g., Khmer, Odia) where monolingual specialists yield significant gains. Rather than enforcing a single universal architecture, we adopt a
language-adaptive framework that switches between
multilingual generalists,
language-specific specialists, and hybrid ensembles based on development performance. Additionally, cross-lingual augmentation via NLLB-200 yielded mixed results, often underperforming native architecture selection and degrading morphologically rich tracks. Our final system achieves an overall macro-averaged F1 score of 0.796 and an average accuracy of 0.826 across all 22 tracks. Code and final test predictions are publicly available at: https://github.com/Maziarkiani/SemEval2026-Task9-Subtask1-Polarization.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.LG
mcdok at SemEval-2026 Task 13: Finetuning LLMs for Detection of Machine-Generated Code
Adam Skurla, Dominik Macko and Jakub Simko
Multi-domain detection of the machine-generated code snippets in various programming
languages is a challenging task. SemEval-2026 Task~13 copes with this challenge in various angles, as a binary detection problem as well as attribution of the source. Specifically, its subtasks also cover generator LLM family detection, as well as a hybrid code co-generated by humans and machines, or adversarially modified codes hiding its origin. Our submitted systems adjusted the existing mdok approach (focused on machine-generated text detection) to these specific kinds of problems by exploring various base models, more suitable for code understanding. The results indicate that the submitted systems are competitive in all three subtasks. However, the margins from the top-performing systems are significant, and thus further improvements are possible.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.AI
ReaGeo: Reasoning-Enhanced End-to-End Geocoding with LLMs
Jian Cui, Zhiyuan Ren, Desheng Weng et al. (+4 more)
This paper proposes ReaGeo, an end-to-end geocoding framework based on large
language models, designed to overcome the limitations of traditional multi-stage approaches that rely on text or vector similarity
retrieval over geographic databases, including workflow complexity, error propagation, and heavy dependence on structured geographic knowledge bases. The method converts geographic coordinates into geohash sequences, reformulating the coordinate prediction task as a text generation problem, and introduces a Chain-of-Thought mechanism to enhance the model's
reasoning over spatial relationships. Furthermore, reinforcement learning with a distance-deviation-based reward is applied to optimize the generation accuracy. Comprehensive experiments show that ReaGeo can accurately handle explicit address queries in single-point predictions and effectively resolve vague relative location queries. In addition, the model demonstrates strong predictive capability for non-point
geometric regions, highlighting its versatility and generalization ability in geocoding tasks.
Read the full abstract ▾
All authors Jian Cui, Zhiyuan Ren, Desheng Weng, Yongqi Zhao, Gong Wenbin, Yu Lei, Zhenning Dong
Computation and Language
CARE: Counselor-Aligned Response Engine for Online Mental-Health Support
Hagai Astrin, Ayal Swaid, Avi Segal et al. (+1 more)
Mental health challenges are increasing worldwide, straining emotional support services and leading to counselor overload. This can result in delayed responses during critical situations, such as suicidal ideation, where timely intervention is essential. While large
language models (LLMs) have shown strong generative capabilities, their application in low-resource
languages, especially in sensitive domains like mental health, remains underexplored. Furthermore, existing LLM-based
agents often struggle to replicate the supportive
language and intervention strategies used by professionals due to a lack of training on large-scale, real-world
datasets. To address this, we propose CARE (Counselor-Aligned Response Engine), a GenAI framework that assists counselors by generating real-time, psychologically aligned response recommendations. CARE fine-tunes open-source LLMs separately for Hebrew and Arabic using curated subsets of real-world crisis conversations. The training data consists of sessions rated as highly effective by professional counselors, enabling the models to capture interaction patterns associated with successful de-escalation. By training on complete conversation histories, CARE maintains the evolving emotional context and dynamic structure of counselor-help-seeker dialogue. In experimental settings, CARE demonstrates stronger semantic and strategic
alignment with gold-standard counselor responses compared to non-specialized LLMs. These findings suggest that domain-specific fine-tuning on expert-validated data can significantly support counselor workflows and improve care quality in low-resource
language contexts.
Read the full abstract ▾
All authors Hagai Astrin, Ayal Swaid, Avi Segal, Kobi Gal
Computation and Language · Cross-listed from cs.AI
Symbolic Grounding Reveals Representational Bottlenecks in Abstract Visual Reasoning
Mohit Vaishnav and Tanel Tammet
Vision–
language models (VLMs) often fail on abstract visual
reasoning benchmarks such as Bongard problems, raising the question of whether the main bottleneck lies in
reasoning or representation. We study this on Bongard-LOGO, a synthetic
benchmark of abstract concept learning with ground-truth generative programs, by comparing end-to-end VLMs on raw images with large
language models (LLMs) given symbolic inputs derived from those images. Using symbolic inputs as a diagnostic probe rather than a practical
multimodal architecture, our Componential–Grammatical (C–G) paradigm reformulates Bongard-LOGO as a symbolic
reasoning task based on LOGO-style action programs or structured descriptions. LLMs achieve large and consistent gains, reaching mid–90s accuracy on Free-form problems, while a strong visual baseline remains near chance under matched task definitions. Ablations on input format, explicit concept
prompts, and minimal visual grounding show that these factors matter much less than the shift from pixels to symbolic structure. These results identify representation as a key bottleneck in abstract visual
reasoning and show how symbolic input can serve as a controlled diagnostic upper bound.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.AI
Evaluating AI Meeting Summaries with a Reusable Cross-Domain Pipeline
Philip Zhong, Don Wang and Jason Zhang
Industrial teams often deploy large
language model features before stable regression or model selection evaluation exists. We present a reusable evaluation system for AI meeting summaries that combines structured ground-truth (GT) construction, fixed candidate generation, claim-grounded scoring, persisted reporting, and a
privacy-bounded online monitoring and nomination interface. The online evidence is not itself a
benchmark:
privacy-safe aggregate exports show active monitoring, hard regime detection, and directional movement without exposing customer data. We
benchmark the offline path on 114 meetings across city_council, private_data, and whitehouse_press_briefings, yielding 340 completed meeting-model pairs and 680 judge runs for gpt-4.1-mini, gpt-5-mini, and gpt-5.1. Under this fixed protocol, accuracy differences are not statistically significant under Holm correction (corrected p-values 0.053-0.448), although gpt-4.1-mini has the highest mean accuracy (0.583); the significant separation is on retention, where gpt-5.1 leads on completeness (0.886) and coverage (0.942). Typed slices isolate whitehouse_press_briefings as an accuracy-hard regime, and a later focused rerun over gpt-4.1, gpt-5-mini, and gpt-5.4 reuses the same stack under the same judges and metrics. This extended preprint keeps those core results aligned with the formal submission while adding a more detailed repository-level account of cross-domain reuse from the companion AI-search paper and an additional typed DeepEval contrastive analysis. Model naming note. Running text uses canonical model names on first introduction. Tables, filenames, and artifact IDs retain compact report labels for consistency with the packaged
benchmark outputs. Table A maps the two conventions and is repeated in Section 4.3 where candidate-generation settings are defined.
Read the full abstract ▾
Computation and Language
Beyond Single Plots: A Benchmark for Question Answering on Multi-Charts
Azher Ahmed Efat, Seok Hwan Song and Wallapak Tavanapong
Charts are widely used to present complex information. Deriving meaningful insights in real-world contexts often requires interpreting multiple related charts together. Research on understanding multi-chart images has not been extensively explored. We introduce PolyChartQA, a mid-scale
dataset specifically designed for question answering over multi-chart images. PolyChartQA comprises 534 multi-chart images (with a total of 2,297 sub-charts) sourced from peer-reviewed computer science research publications and 2,694 QA pairs. We evaluate the performance of nine state-of-the-art
Multimodal Language Models (MLMs) on PolyChartQA across question type, difficulty, question source, and key structural characteristics of multi-charts. Our results show a 27.4% LLM-based accuracy (L-Accuracy) drop on human-authored questions compared to MLM-generated questions, and a 5.39% L-accuracy gain with our proposed prompting method.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.LG
Sub-Token Routing for KV Cache Compression
Wei Jiang and Wei Wang
Transformer inference often requires a large KV cache, especially for long-context
language modeling and
multimodal generation. Existing compression methods usually reduce cache cost by selecting, evicting, quantizing, or compressing cached
tokens, or by reducing the visual-
token sequence before
language-model inference. We introduce sub-
token routing, a KV-compression method that adds a finer control axis inside retained
tokens. It splits each retained value vector into groups and keeps only selected groups, while leaving query and key states unchanged. The method is designed to work after
token-level reduction. First, a
token-reduction method determines which
tokens are retained. Then, sub-
token routing compresses the value states inside those retained
tokens. Experiments under matched KV budgets show that adding sub-
token routing improves
token-level reduction performance in both LLM and VLM settings, including Quest on LLaMA-2-7B and Qwen2.5-7B, and FastV/VisionZip across LLaVA and Qwen-VL models. The gains are larger at smaller KV budgets, suggesting that value-group routing is especially useful when further
token removal becomes costly. Overall,
token-level reduction and sub-
token routing provide complementary ways to reduce KV cost.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.AI
Ideological Bias in LLMs' Economic Causal Reasoning
Donggyu Lee, Hyeok Yun, Jungwon Kim et al. (+4 more)
Do large
language models (LLMs) exhibit systematic ideological bias when
reasoning about economic causal effects? As LLMs are increasingly used in policy analysis and economic reporting, where directionally correct causal judgments are essential, this question has direct practical stakes. We present a systematic evaluation by extending the EconCausal
benchmark with ideology-contested cases - instances where intervention-oriented (pro-government) and
market-oriented (pro-
market) perspectives predict divergent causal signs. From 10,490 causal triplets (treatment-outcome pairs with empirically verified effect directions) derived from top-tier economics and finance journals, we identify 1,056 ideology-contested instances and evaluate 20 state-of-the-art LLMs on their ability to predict empirically supported causal directions. We find that ideology-contested items are consistently harder than non-contested ones, and that across 17 of 20 models, accuracy is systematically higher when the empirically verified causal sign aligns with intervention-oriented expectations than with
market-oriented ones. Moreover, when models err, their incorrect predictions disproportionately lean intervention-oriented, and this directional skew is not eliminated by one-shot in-context prompting. These results highlight that LLMs are not only less accurate on ideologically contested economic questions, but systematically less reliable in one ideological direction than the other, underscoring the need for direction-aware evaluation in high-stakes economic and policy settings.
Read the full abstract ▾
All authors Donggyu Lee, Hyeok Yun, Jungwon Kim, Junsik Min, Sungwon Park, Sangyoon Park, Jihee Kim
Computation and Language · Cross-listed from cs.LG
Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning
Yongcan Yu, Lingxiao He, Jian Liang et al. (+5 more)
Test-time reinforcement learning (TTRL) always adapts models at inference time via pseudo-labeling, leaving it vulnerable to spurious optimization signals from label noise. Through an empirical study, we observe that responses with medium consistency form an ambiguity region and constitute the primary source of reward noise. Crucially, we find that such spurious signals can be even amplified through group-relative advantage estimation. Motivated by these findings, we propose a unified framework, Debiased and Denoised test-time Reinforcement Learning (DDRL), to mitigate spurious signals. Concretely, DDRL first applies a frequency-based sampling strategy to exclude ambiguous samples while maintaining a balanced set of positive and negative examples. It then adopts a debiased advantage estimation with fixed advantages, removing the bias introduced by group-relative policy optimization. Finally, DDRL incorporates a consensus-based off-policy refinement stage, which leverages the rejection-sampled
dataset to enable efficient and stable model updates. Experiments on three large
language models across multiple mathematical
reasoning benchmarks demonstrate that DDRL consistently outperforms existing TTRL baselines. The code will soon be released at https://github.com/yuyongcan/DDRL.
Read the full abstract ▾
All authors Yongcan Yu, Lingxiao He, Jian Liang, Kuangpu Guo, Meng Wang, Qianlong Xie, Xingxing Wang, Ran He
Computation and Language
When Bigger Isn't Better: A Comprehensive Fairness Evaluation of Political Bias in Multi-News Summarisation
Nannan Huang, Iffat Maab and Junichi Yamagishi
Multi-document news summarisation systems are increasingly adopted for their convenience in processing vast daily news content, making
fairness across diverse political perspectives critical. However, these systems can exhibit political bias through unequal representation of viewpoints, disproportionate emphasis on certain perspectives, and systematic underrepresentation of minority voices. This study presents a comprehensive evaluation of such bias in multi-document news summarisation using FairNews, a
dataset of complete news articles with political orientation labels, examining how large
language models (LLMs) handle sources with varying political leanings across 13 models and five
fairness metrics. We investigate both baseline model performance and effectiveness of various debiasing interventions, including
prompt-based and judge-based approaches. Our findings challenge the assumption that larger models yield fairer outputs, as mid-sized variants consistently outperform their larger counterparts, offering the best balance of
fairness and efficiency.
Prompt-based debiasing proves highly model dependent, while entity sentiment emerges as the most stubborn
fairness dimension, resisting all intervention strategies tested. These results demonstrate that
fairness in multi-document news summarisation requires multi-dimensional evaluation frameworks and targeted, architecture-aware debiasing rather than simply scaling up.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.CR
CI-Work: Benchmarking Contextual Integrity in Enterprise LLM Agents
Wenjie Fu, Xiaoting Qin, Jue Zhang et al. (+5 more)
Enterprise LLM
agents can dramatically improve workplace productivity, but their core capability, retrieving and using internal context to act on a user's behalf, also creates new risks for sensitive information leakage. We introduce CI-Work, a Contextual Integrity (CI)-grounded
benchmark that simulates enterprise workflows across five information-flow directions and evaluates whether
agents can convey essential content while withholding sensitive context in dense
retrieval settings. Our evaluation of frontier models reveals that
privacy failures are prevalent (violation rates range from 15.8%-50.9%, with leakage reaching up to 26.7%) and uncovers a counterintuitive trade-off critical for industrial deployment: higher task utility often correlates with increased
privacy violations. Moreover, the massive scale of enterprise data and potential user behavior further amplify this vulnerability. Simply increasing model size or
reasoning depth fails to address the problem. We conclude that safeguarding enterprise workflows requires a paradigm shift, moving beyond model-centric scaling toward context-centric architectures.
Read the full abstract ▾
All authors Wenjie Fu, Xiaoting Qin, Jue Zhang, Qingwei Lin, Lukas Wutschitz, Robert Sim, Saravan Rajmohan, Dongmei Zhang
Computation and Language
Explainable Disentangled Representation Learning for Generalizable Authorship Attribution in the Era of Generative AI
Hieu Man, Van-Cuong Pham, Nghia Trung Ngo et al. (+2 more)
Learning robust representations of authorial style is crucial for authorship attribution and AI-generated text detection. However, existing methods often struggle with content-style
entanglement, where models learn spurious correlations between authors' writing styles and topics, leading to poor generalization across domains. To address this challenge, we propose Explainable Authorship Variational Autoencoder (EAVAE), a novel framework that explicitly disentangles style from content through architectural separation-by-design. EAVAE first pretrains style encoders using supervised contrastive learning on diverse authorship data, then finetunes with a Variational Autoencoder (VEA) architecture using separate encoders for style and content representations. Disentanglement is enforced through a novel discriminator that not only distinguishes whether pairs of style/content representations belong to the same or different authors/content sources, but also generates natural
language explanation for their decision, simultaneously mitigating confounding information and enhancing interpretability. Extensive experiments demonstrate the effectiveness of EAVAE. On authorship attribution, we achieve state-of-the-art performance on various
datasets, including Amazon Reviews, PAN21, and HRS. For AI-generated text detection, EAVAE excels in few-shot learning over the M4
dataset. Code and data repositories are available online\footnote{https://github.com/hieum98/avae} \footnote{https://huggingface.co/collections/Hieuman/document-level-authorship-
datasets}.
Read the full abstract ▾
All authors Hieu Man, Van-Cuong Pham, Nghia Trung Ngo, Franck Dernoncourt, Thien Huu Nguyen
Computation and Language
Cross-Entropy Is Load-Bearing: A Pre-Registered Scope Test of the K-Way Energy Probe on Bidirectional Predictive Coding
Jon-Paul Cacioli
Cacioli (2026) showed that the K-way energy probe on standard discriminative predictive coding networks reduces approximately to a monotone function of the log-softmax margin. The reduction rests on five assumptions, including cross-
entropy (CE) at the output and effectively feedforward inference dynamics. This pre-registered study tests the reduction's sensitivity to CE removal using two conditions: standard PC trained with MSE instead of CE, and bidirectional PC (bPC; Oliviers, Tang & Bogacz, 2025). Across 10 seeds on CIFAR-10 with a matched 2.1M-parameter backbone, we find three results. The negative result replicates on standard PC: the probe sits below softmax (Delta = -0.082, p < 10^-6). On bPC the probe exceeds softmax across all 10 seeds (Delta = +0.008, p = 0.000027), though a pre-registered manipulation check shows that bPC does not produce materially greater latent movement than standard PC at this scale (ratio 1.6, threshold 10). Removing CE alone without changing inference dynamics halves the probe-softmax gap (Delta_MSE = -0.037 vs Delta_stdPC = -0.082). CE is a major empirically load-bearing component of the decomposition at this scale. CE training produces output logit norms approximately 15x larger than MSE or bPC training. A post-hoc temperature scaling ablation decomposes the probe-softmax gap into two components: approximately 66% is attributable to logit-scale effects removable by temperature rescaling, and approximately 34% reflects a scale-invariant ranking advantage of CE-trained representations. We use "metacognitive" operationally to denote Type-2 discrimination of a readout over its own Type-1 correctness, not to imply human-like introspective access.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.AI
Spatial Metaphors for LLM Memory: A Critical Analysis of the MemPalace Architecture
Robin Dey and Panyanon Viradecha
MemPalace is an open-source AI
memory system that applies the ancient method of loci (
memory palace) spatial metaphor to organize long-term
memory for large
language models; launched in April 2026, it accumulated over 47,000 GitHub
stars in its first two weeks and claims state-of-the-art
retrieval performance on the LongMemEval
benchmark (96.6% Recall@5) without requiring any LLM inference at write time. Through independent codebase analysis,
benchmark replication, and comparison with competing systems, we find that MemPalace's headline
retrieval performance is attributable primarily to its verbatim storage philosophy combined with ChromaDB's default
embedding model (all-MiniLM-L6-v2), rather than to its spatial organizational metaphor per se – the palace hierarchy (Wings->Rooms->Closets->Drawers) operates as standard vector database metadata filtering, an effective but well-established technique. However, MemPalace makes several genuinely novel contributions: (1) a contrarian verbatim-first storage philosophy that challenges extraction-based competitors, (2) an extremely low wake-up cost (approximately 170
tokens) through its four-layer
memory stack, (3) a fully deterministic, zero-LLM write path enabling offline operation at zero API cost, and (4) the first systematic application of spatial
memory metaphors as an organizing principle for AI
memory systems. We also note that the competitive landscape is evolving rapidly, with Mem0's April 2026
token-efficient
algorithm raising their LongMemEval score from approximately 49% to 93.4%, narrowing the gap between extraction-based and verbatim approaches. Our analysis concludes that MemPalace represents significant architectural insight wrapped in overstated claims – a pattern common in rapidly adopted open-source projects where marketing velocity exceeds scientific rigor.
Read the full abstract ▾
Computation and Language
Do LLM Decoders Listen Fairly? Benchmarking How Language Model Priors Shape Bias in Speech Recognition
Srishti Ginjala, Eric Fosler-Lussier, Christopher W. Myers et al. (+1 more)
As pretrained large
language models replace task-specific decoders in
speech recognition, a critical question arises: do their text-derived priors make recognition fairer or more biased across demographic groups? We evaluate nine models spanning three architectural generations (CTC with no
language model, encoder-decoder with an implicit LM, and LLM-based with an explicit pretrained decoder) on about 43,000 utterances across five demographic axes (ethnicity, accent, gender, age, first
language) using Common Voice 24 and Meta's Fair-
Speech, a controlled-
prompt dataset that eliminates vocabulary confounds. On clean audio, three findings challenge assumptions: LLM decoders do not amplify racial bias (Granite-8B has the best ethnicity
fairness, max/min WER = 2.28); Whisper exhibits pathological
hallucination on Indian-accented
speech with a non-monotonic insertion-rate spike to 9.62% at large-v3; and audio compression predicts accent
fairness more than LLM scale. We then stress-test these findings under 12 acoustic degradation conditions (noise, reverberation, silence injection, chunk masking) across both
datasets, totaling 216 inference runs. Severe degradation paradoxically compresses
fairness gaps as all groups converge to high WER, but silence injection amplifies Whisper's accent bias up to 4.64x by triggering demographic-selective
hallucination. Under masking, Whisper enters catastrophic repetition loops (86% of 51,797 insertions) while explicit-LLM decoders produce 38x fewer insertions with near-zero repetition; high-compression audio encoding (Q-former) reintroduces repetition pathology even in LLM decoders. These results suggest that audio encoder design, not LLM scaling, is the primary lever for equitable and robust
speech recognition.
Read the full abstract ▾
All authors Srishti Ginjala, Eric Fosler-Lussier, Christopher W. Myers, Srinivasan Parthasarathy
Computation and Language
Listen and Chant Before You Read: The Ladder of Beauty in LM Pre-Training
Yoshinori Nomura
We show that pre-training a
Transformer on music before
language significantly accelerates
language acquisition. Using piano performances (MAESTRO
dataset), a developmental pipeline – music $\to$ poetry $\to$ prose – yields a $17.5\%$ perplexity improvement over random initialization ($p < 0.001$, 5 seeds), with music and poetry improving orthogonal model components (internal computation and
embeddings, respectively). Convergence tests confirm that this is not a transient head start: at $d\!=\!64$, multi-seed validation (5 seeds) shows a persistent 5.5% gap at plateau ($p = 0.017$), with the pipeline converging faster and to a lower loss in every run. Real music matches the transfer ceiling of synthetic patterns with one-third the data, and scaling experiments reveal that optimal pre-training data volume shifts with model capacity ($-3\% \to +3\% \to +6\%$ advantage of larger
datasets from $d\!=\!16$ to $d\!=\!64$). Across the scales we study ($d\!\in\!\{16,32,64\}$, up to ${\sim}400$K parameters), these results suggest a capacity-dependent data curation principle and indicate that structured human creative outputs can provide an efficient pre-training substrate for small
language models; stronger conclusions at modern pre-training scale will require substantially larger experiments.
Read the full abstract ▾
Computation and Language
When Agents Look the Same: Quantifying Distillation-Induced Similarity in Tool-Use Behaviors
Chenghao Yang, Yuning Zhang, Zhoufutu Wen et al. (+4 more)
Model
distillation is a primary driver behind the rapid progress of LLM
agents, yet it often leads to behavioral homogenization. Many emerging
agents share nearly identical
reasoning steps and failure modes, suggesting they may be distilled echoes of a few dominant teachers. Existing metrics, however, fail to distinguish mandatory behaviors required for task success from non-mandatory patterns that reflect a model's autonomous preferences. We propose two complementary metrics to isolate non-mandatory behavioral patterns: Response Pattern Similarity (RPS) for verbal
alignment and Action Graph Similarity (AGS) for tool-use habits modeled as directed graphs. Evaluating 18 models from 8 providers on $\tau$-Bench and $\tau^2$-Bench against Claude Sonnet 4.5 (thinking), we find that within-family model pairs score 5.9 pp higher in AGS than cross-family pairs, and that Kimi-K2 (thinking) reaches 82.6% $S_{\text{node}}$ and 94.7% $S_{\text{dep}}$, exceeding Anthropic's own Opus 4.1. A controlled
distillation experiment further confirms that AGS distinguishes teacher-specific convergence from general improvement. RPS and AGS capture distinct behavioral dimensions (Pearson $r$ = 0.491), providing complementary diagnostic signals for behavioral convergence in the
agent ecosystem. Our code is available at https://github.com/Syuchin/AgentEcho.
Read the full abstract ▾
All authors Chenghao Yang, Yuning Zhang, Zhoufutu Wen, Tao Gong, Jiaheng Liu, Qi Chu, Nenghai Yu
Computation and Language · Cross-listed from cs.LG
Abbas Zeitoun, Lucas Torroba-Hennigen and Yoon Kim
LLM architecture research generally aims to maximize model quality subject to fixed compute/latency budgets. However, many applications of interest such as edge and on-device deployment are further constrained by the model's
memory footprint, thus motivating parameter-efficient architectures for
language modeling. This paper describes a simple architecture that improves the parameter-efficiency of LLMs. Our architecture makes use of looped
Transformers as a core primitive, which reuse
Transformer layers across depth and are thus more parameter-efficient than ordinary (depth-matched)
Transformers. We organize the looped
Transformer into three blocks–begin, middle, and end blocks–where each block itself consists of multiple
Transformer layers, and only the middle block is applied recurrently across depth. We augment the looped middle block with hyper-connections (Xie et al., 2026), which expand the residual stream into
matrix-valued residual streams. Hyper-connections are applied only after each loop, and therefore add minimal new parameters and compute cost. Across various model scales, we find that our Hyper-Connected Looped
Transformer (Hyperloop
Transformer) is able to perform well compared to depth-matched
Transformer and mHC
Transformer baselines despite using approximately 50% fewer parameters. This performance persists through post-training weight quantization, thus positioning Hyperloop
Transformers as an attractive architecture for
memory-efficient
language modeling.
Read the full abstract ▾
Computation and Language
Planning Beyond Text: Graph-based Reasoning for Complex Narrative Generation
Hanwen Gu, Chao Guo, Junle Wang et al. (+2 more)
While LLMs demonstrate remarkable fluency in narrative generation, existing methods struggle to maintain global narrative coherence, contextual logical consistency, and smooth character development, often producing monotonous scripts with structural fractures. To this end, we introduce PLOTTER, a framework that performs narrative planning on structural graph representations instead of the direct sequential text representations used in existing work. Specifically, PLOTTER executes the Evaluate-Plan-Revise cycle on the event graph and character graph. By diagnosing and repairing issues of the graph
topology under rigorous logical constraints, the model optimizes the causality and narrative skeleton before complete context generation. Experiments demonstrate that PLOTTER significantly outperforms representative baselines across diverse narrative scenarios. These findings verify that planning narratives on structural graph representations-rather than directly on text-is crucial to enhance the long context
reasoning of LLMs in complex narrative generation.
Read the full abstract ▾
All authors Hanwen Gu, Chao Guo, Junle Wang, Wenda Xie, Yisheng Lv
Computation and Language
Unlocking the Power of Large Language Models for Multi-table Entity Matching
Yingkai Tang, Taoyu Su, Wenyuan Zhang et al. (+2 more)
Multi-table entity matching (MEM) addresses the limitations of dual-table approaches by enabling simultaneous identification of equivalent entities across multiple data sources without unique identifiers. However, existing methods relying on pre-trained
language models struggle to handle semantic inconsistencies caused by numerical attribute variations. Inspired by the powerful
language understanding capabilities of large
language models (LLMs), we propose a novel LLM-based framework for multi-table entity matching, termed LLM4MEM. Specifically, we first propose a multi-style
prompt-enhanced LLM attribute coordination module to address semantic inconsistencies. Then, to alleviate the matching efficiency problem caused by the surge in the number of entities brought by multiple data sources, we develop a transitive consensus
embedding matching module to tackle entity
embedding and pre-matching issues. Finally, to address the issue of noisy entities during the matching process, we introduce a density-aware
pruning module to optimize the quality of multi-table entity matching. We conducted extensive experiments on 6 MEM
datasets, and the results show that our model improves by an average of 5.1% in F1 compared with the baseline model. Our code is available at https://github.com/Ymeki/LLM4MEM.
Read the full abstract ▾
All authors Yingkai Tang, Taoyu Su, Wenyuan Zhang, Xiaoyang Guo, Tingwen Liu