Peer Revenue Impact factor: volatile

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Computation and Language

cs.CL Watch Computation and Language

Monday 14 September

Computation and Language

Dream-RSI: Recursive Self-Improvement through Evolving Worlds

Tong Zheng, Xidong Wu, Zheng Zhang et al. (+14 more)

Recursive self-improvement is becoming essential for autonomous AI agents, whose progress depends on discovering high-value solutions across complex domains. Effective exploration drives this process, yet managing and improving exploration strategies remains a major bottleneck. Current systems face a fundamental dilemma: fixed strategies fail to adapt as search spaces scale, while online policy optimization must navigate vast meta-search spaces under delayed, expensive feedback from long-horizon rollouts. We introduce Dream-RSI, a framework for scalable, recursively self-improving exploration. A lightweight orchestration layer makes exploration explicit and programmable while leaving the underlying base agent unchanged. Our key insight is that accumulated discovery history can act as a replay simulator over the realized search space. By dreaming within this simulator built from historical discovery trees, Dream-RSI obtains immediate, low-cost off-policy feedback to evaluate and refine exploration policies without repeated, expensive online evaluation. The improved policy is then redeployed online to drive further discovery, continuously expanding the simulator pool in a self-improving loop. Across 9 tasks in 4 domains, Dream-RSI achieves competitive quality and improves discovery efficiency in several settings.
Read the full abstract

All authors Tong Zheng, Xidong Wu, Zheng Zhang, Zhankui He, Chaoyi Zhang, Benjamin Coleman, Ruoqiao Wei, Di Bai, Haolin Liu, Rui Liu, Xue Wang, Yue Zhuan, Wang-Cheng Kang, Renkai Xiang, Heng Huang, Xinwu Cheng, Yunsong Guo

Computation and Language

ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement

Siwei Wu, Jincheng Ren, Yizhi Li et al. (+12 more)

Recent work extends recursive self-improvement (RSI) to agent harnesses for long-horizon coding and terminal tasks, enabling agents to improve execution mechanisms from experience. However, generalizable harness RSI remains challenging. First, evolving harnesses on evaluation benchmarks or their subsets makes it difficult to distinguish reusable improvements from benchmark-specific adaptation. Second, single-trajectory updates can conflate systematic harness deficiencies with instance-specific reasoning and solution details, producing modifications that transfer poorly to unseen tasks. Third, localizing recurring behavioral deficiencies within monolithic harnesses is difficult, while whole-harness optimization can entangle unrelated mechanisms and complicate attribution and validation. We propose ModularRSI, a benchmark-disjoint, contrastive, and modular framework for generalizable harness evolution. ModularRSI contrasts successful and failed trajectories for the same task and aggregates evidence across tasks to identify recurring behavioral deficiencies. It decomposes the evolvable harness into five functional modules: Agent Loop, Tool Use, Observation Management, Context Management, and Task Completion Detection. Each module evolves independently within a restricted modification scope, followed by an integration stage that combines the evolved modules into a unified harness and resolves potential conflicts. To support benchmark-disjoint evolution, we curate 2,000 executable evolution tasks from external sources that are disjoint from downstream evaluation benchmarks. Experiments on TB2.0 and SWE-Bench Verified show consistent improvements on unseen in-domain and cross-domain tasks, with the evolved harness also transferring across different foundation models.
Read the full abstract

All authors Siwei Wu, Jincheng Ren, Yizhi Li, Haau-Sing Li, Chengran Yang, Xudong Ma, Yuxuan Zhang, Weicheng Gu, Jian Yang, Riza Batista-Navarro, Chuanyi Zhang, Xianglong Liu, Ming Zhou, Bryan Dai, Chenghua Lin

Sunday 13 September

Computation and Language

Composable Parametric Demographic Injection for Values Survey Simulation

Xinyuan Cao, Qingyi Pan, Bangde Du et al. (+7 more)

Large language models (LLMs) are increasingly used as simulated respondents in computational social science, yet accurately reproducing population-specific heterogeneous response distributions remains challenging. Existing methods such as demographic prompting are sensitive to prompt design and increase inference overhead, while parameter-based methods struggle to reuse demographic information efficiently, limiting generalization to unseen combinations. In this regard, we propose PARADE, a composable PARAmetric DEmographic injection framework that represents each demographic attribute value with a reusable and composable LoRA module. Specifically, PARADE separates task-common survey capability from demographic-specific value shifts via a shared Task LoRA and attribute-level Demographic LoRAs, with composition calibration to reduce parameter interference. At inference time, target population models can be constructed on demand by recombining the relevant modules, including demographic combinations not observed during training. Extensive experiments on the World Values Survey and SocioBench across three backbone models show that PARADE achieves strong population-level distribution alignment while maintaining competitive predictive performance, reducing KL divergence by up to 52.8% relative to the strongest baseline.
Read the full abstract

All authors Xinyuan Cao, Qingyi Pan, Bangde Du, Yujia Zhou, Hexi Wang, Weihang Su, Yiqun Liu, Yueyue Wu, Min Zhang, Qingyao Ai

Computation and Language · Cross-listed from cs.NE

From Hand-Crafted to LLM-Based Variation Operators in Metaheuristics: A Tutorial

Camilo Chacón Sartori, Guillem Rodríguez-Corominas and Christian Blum

Large language models (LLMs) are increasingly being employed as variation operators in metaheuristics, generating or modifying candidate solutions, heuristics, or programs inside iterative search loops. This shift reframes variation as a model call conditioned on different types of information. We introduce an operator-level framework with two descriptors: (1) the type of prompt-conditioning information at variation time (Numeric, Symbolic, Linguistic), and (2) artifact persistence, identifying what survives the model call (Transient, Amortized, Transfer). The tutorial shows how to classify, build, and select these operators through a worked build template, a method survey, an evidence table, and a cost-aware decision guide.
Read the full abstract

Computation and Language

SignTrace: Describe a Sign, Find the Word

Zengji Tu, Xingye Zhu, Ningjing Wang et al. (+3 more)

Identifying an unfamiliar sign is difficult when a learner remembers its movement but does not know its meaning or formal feature codes. SignTrace addresses this longstanding reverse-lookup problem through natural-language access to a Chinese sign-language dictionary. The system integrates LLM-based dictionary enrichment, action extraction, dictionary-style rewriting, seven-channel retrieval, and candidate reranking over 6,699 entries. It has been deployed for user trials and has received positive informal feedback. Evaluation on a dictionary-derived benchmark of 500 movement-description queries yields 94.0% Hit@1, 97.4% Hit@9, and a mean reciprocal rank of 0.9540. Reranking increases Hit@1 from 71.8% to 94.0%, while component analyses show the contribution of enriched entry descriptions. Median query-processing time is 13.37 seconds with six concurrent queries. By connecting everyday movement descriptions to documented signs and meanings, SignTrace provides a practical tool for identifying unfamiliar signs. Dictionary-derived wording and prior selection within the benchmark limit generalization to descriptions independently produced by users.
Read the full abstract

All authors Zengji Tu, Xingye Zhu, Ningjing Wang, Tingyi Huang, Yangjunfeng Zhu, Dai Wan

Computation and Language

SlideLab: Audience-Centered Scientific Slide Generation and Evaluation

Vidushee Vats, Karun Sharma and Yuxia Wang

Scientific presentations are more than summaries of research papers. They need to present the work in a coherent sequence, explain the main ideas clearly, and help the audience follow the presentation. We present SlideLab, a training-free multi-agent framework for generating scientific presentations from research papers. SlideLab first plans the presentation narrative, then builds and iteratively refines a shared slide deck using agents for content planning, visual generation, layout refinement, and grounding verification. In a blind human preference study, SlideLab was preferred over both open-source and commercial systems on 77% of papers while using roughly 4 times fewer inference tokens than the strongest open-source baseline. We also introduce ConfArena, an audience-oriented evaluation framework that simulates a conference room and assesses presentations slide by slide. ConfArena matches human system rankings and detects injected presentation problems, including falsified numbers, degraded figures, dropped slides, and shuffled slide order.
Read the full abstract

Computation and Language

Cartograph: Federated Tool Discovery with Operator-Attested Retrieval for AI Agents

Justice Owusu Agyemang, Michael Agyare, Kwame Opuni-Boachie Obour Agyekum et al. (+3 more)

The Model Context Protocol (MCP) enables AI agents to discover and call tools, but loading every definition becomes expensive as connected catalogs grow. We present Cartograph, a federated MCP proxy that changes agent-visible tool discovery from $O(n)$ catalog traversal to $O(k)$ progressive disclosure. Cartograph combines three mechanisms: (1) operator-attested capability cards, Ed25519-signed descriptions generated under the deploying operator's control rather than ranked publisher copy; (2) Rift, a three-layer confusable-cluster analysis comprising density clustering, query-margin analysis, and token diagnosis; and (3) two-stage retrieval, which ranks servers before tools. On a 22-server, 374-tool deployment, Cartograph exposes three proxy tools instead of 374 definitions. A 49-query author-constructed benchmark yields R@5 of 0.816, compared with 0.592 for a Jaccard keyword baseline, while a measured top-5 discovery exchange uses 475 tokens rather than 42,450 under the stated full-catalog accounting. Rift identifies 49 confusable clusters, including four HIGH-risk clusters in bootstrap-generated cards. An exploratory comparison of 119 LLM-generated descriptions removes the observed zero-distance cluster but shows that mixing card-generation regimes can reduce R@5. Gateway measurements over ten trials add 5ms mean latency (0.8%) relative to direct stdio MCP calls. Cartograph is complementary to code-execution approaches: it controls which tool descriptions are surfaced and records the provenance of the descriptions used for ranking for each query.
Read the full abstract

All authors Justice Owusu Agyemang, Michael Agyare, Kwame Opuni-Boachie Obour Agyekum, Kwame Agyeman-Prempeh Agyekum, Francisca Adoma Acheampong, Jerry John Kponyo

Computation and Language

Making Political Text Scaling Comparable: Infrastructure and Hyperparameter Sensitivity for 17 Algorithms

Patrick Parschan

Computational text-based ideal point estimation (CT-IPE) methods are usually compared as named algorithms, yet applying them involves numerous researcher choices that configure how political text is turned into position estimates. This paper argues that CT-IPE methods are better understood as configurable measurement pipelines than as fixed estimators. Building on a large-scale comparative experiment spanning 17 CT-IPE algorithms, 5,537 experimental runs, and approximately 4.25 million left-right position estimates, I describe the shared infrastructure that makes these heterogeneous methods jointly executable and quantify how sensitive their estimates are to alternative hyperparameter choices. Variance-partitioning and SHAP-based sensitivity analyses show that, for most algorithms, hyperparameter profiles explain little residual variance through a shared shift: 13 of the 17 algorithms exhibit ICC values below .10. Where this profile-level sensitivity is present, it is concentrated in a small number of consequential researcher choices, most notably the selection of the underlying language or embedding model, the seed keyword lists that anchor the construct, and the number of topics.
Read the full abstract

Computation and Language

The Imitation Game: When LLMs Learn to Reason Like Programs via Code-Centric Reasoning Data Synthesis

Jinyang Zhang, Weibin Liao, Keqin Bao et al. (+10 more)

Large Language Models (LLMs) excel at programming tasks but frequently fail at deterministic, fine-grained reasoning in natural language, relying heavily on semantic approximations rather than robust symbolic execution. To bridge this gap, we propose MIMIC, a framework that leverages executable code as a rigorous medium for reasoning data synthesis. MIMIC fundamentally transforms algorithms into verifiable reasoning trajectories through narrative fusion, code-guided test synthesis, and dynamic code instrumentation. Crucially, these explicit intermediate execution states naturally form a Code-Instrumented Reward (CIR), providing dense, high-fidelity process supervision for reinforcement learning without external reward models. Extensive evaluations reveal that models trained via SFT and GRPO on our synthesized dataset achieve substantial, consistent gains. Our method significantly elevates accuracy across general reasoning, complex mathematical benchmarks, and fine-grained deterministic tasks, demonstrating that the procedural rigor of executable code can effectively unlock and enhance the generalized reasoning capabilities of LLMs. Our code and data are available at https://github.com/zjy1298/MIMIC.
Read the full abstract

All authors Jinyang Zhang, Weibin Liao, Keqin Bao, Sihang Li, Shaobo Wang, Muyang Ye, Hongxin Ding, Yue Fang, Tianyi Tang, Fei Huang, Kexin Yang, Xingzhang Ren, Dayiheng Liu

Computation and Language

The Immutable Past: Formalizing State Mutability and Conflict Resolution in Mutable RAG

Hamed HaddadPajouh and Amir AmiriTabat

Retrieval-Augmented Generation (RAG) serves as the primary memory architecture for long-horizon autonomous agents. However, treating shared memory as an append-only stream introduces Semantic Shadowing, a critical failure mode where conflicting historical observations accumulate and statistically dominate valid recent updates. In dynamic environments, this results in severe state divergence as agents retrieve and act upon obsolete facts. This paper formalizes the mechanics of State Mutability to prove that standard dense retrieval suffers from Asymptotic Recall Decay. Furthermore, we formally demonstrate a Majority Vote Trap, revealing that increasing the retrieval context window paradoxically degrades generation accuracy by diluting the attention mechanism under conditions of semantic equivalence. To resolve this, we introduce GC-Mem (Garbage Collection for Memory), a strict inference-time consistency protocol. Unlike heuristic time-decay mechanisms—which indiscriminately destroy valid long-term memory—GC-Mem relies purely on a temporal dominance operator ($\Phi_{\mathcal{T}}$) paired with contradiction detection to surgically excise shadowed context. Evaluated across a rigorous, behaviorally inferred benchmark of 137,760 memory chunks and continuous accumulation sweeps, standard RAG and timestamp re-ranking baselines experience severe degradation. In contrast, GC-Mem empirically recovers $>90\%$ conflict resolution accuracy. We establish strict precision and recall deployment thresholds, ensuring state convergence where standard mutable RAG fundamentally fails.
Read the full abstract

Computation and Language

Efficient Multimodal Generative Recommendation with Latent Narrative Reasoning

Chenxing Wang, Nantao Zheng, Hao Miao et al. (+5 more)

Generative recommendation reformulates item prediction as semantic identifier generation, yet episodic content introduces a fundamentally different setting where the target is determined by narrative evolution rather than user preference. This task requires models to understand multimodal storyline progression while addressing the efficiency challenges caused by redundant visual contexts and costly explicit reasoning generation. We propose NarraLite, an efficient multimodal generative recommendation framework that jointly compresses perception and reasoning. Specifically, Progressive Spectral Compression selectively distills long visual contexts into compact narrative-relevant evidence, preserving transition-critical information while reducing redundant visual computation. Latent Narrative Reasoning introduces context-routed latent reasoning tokens and aligns their contextualized representations with future continuation semantics, enabling implicit narrative inference without autoregressively decoding textual rationales. We further establish a user-agnostic multimodal benchmark for short-form drama continuation across UGC, PGC, and OOD settings. Extensive experiments demonstrate that NarraLite consistently improves continuation accuracy, narrative coherence, and robustness over existing approaches, while achieving a favorable accuracy–efficiency trade-off.
Read the full abstract

All authors Chenxing Wang, Nantao Zheng, Hao Miao, Juyuan Wang, Xinke Jiang, Yuchen Fang, Aolin Li, Haijun Wu

Computation and Language · Cross-listed from cs.LG

POSPAN: Position-Constrained Span Masking for Language Model Pre-training

Zhenyu Zhang, Lei Shen, Yuming Zhao et al. (+2 more)

Span-level masked language modeling (MLM) has shown to be advantageous to pre-trained language models over the original single-token MLM, as entities/phrases and their dependencies are critical to language understanding. Previous works only consider span length with some discrete distributions, while the dependencies among spans are ignored, i.e., assuming that the positions of masked spans are uniformly distributed. In this paper, we present POSPAN, a general framework to allow diverse position-constrained span masking strategies via the combination of span length distribution and position constraint distribution, which unifies all existing span-level masking methods. To verify the effectiveness of POSPAN in pre-training, we evaluate it on the datasets from several NLU benchmarks. Experimental results indicate that the position constraint is capable of enhancing span-level masking broadly, and our best POSPAN setting consistently outperforms its span-length-only counterparts and vanilla MLM. We also conduct theoretical analysis for the position constraint in masked language models to shed light on the reason why POSPAN works well, demonstrating the rationality and necessity of POSPAN.
Read the full abstract

All authors Zhenyu Zhang, Lei Shen, Yuming Zhao, Meng Chen, Xiaodong He

Computation and Language · Cross-listed from cs.LG

HintMiner: Automatic Question Hints Mining From Q&A Web Posts with Language Model via Self-Supervised Learning

Zhenyu Zhang and JiuDong Yang

Users often need ask questions and seek answers online. The Question - Answering (QA) forums such as Stack Overflow cannot always respond to the questions timely and properly. In this paper, we propose HintMiner, a novel automatic question hints mining tool for users to help them find answers. HintMiner leverages the machine comprehension and sequence generation techniques to automatically generate hints for users' questions. It firstly retrieve many web Q&A posts and then extract some hints from the posts using MiningNet that is built via a language model. Using the huge amount of online Q&A posts, we design a self-supervised objective to train the MiningNet that is a neural encoder-decoder model based on the transformer and copying mechanisms. We have evaluated HintMiner on 60,000 Stack Overflow questions. The experiment results show that the proposed approach is effective. For example, HintMiner achieves an average BLEU score of 36.17% and an average ROUGE-2 score of 36.29%. Our tool and experimental data are publicly available.
Read the full abstract

Computation and Language

Towards Scalable RLVR: Multimodal Instruction Following Data Synthesis and Distillation

Yirong Zeng, Zhang Sai, Yuxian Wang et al. (+4 more)

Multimodal instruction following (MMIF) is crucial for building generalist agents. However, current training paradigms rely heavily on Supervised Fine-Tuning (SFT), which often leads to surface-level pattern matching and degrades general capabilities. While Reinforcement Learning with Verifiable Rewards (RLVR) offers a promising alternative, its scalability in MMIF is severely bottlenecked by the scarcity of high-quality, RL-ready multimodal data. To bridge this gap, we present MIFS (Multimodal Instruction Following Synthesis), a systematic pipeline designed to generate RL-ready multimodal data. Specifically, MIFS introduces a generative constraint protocol to synthesize diverse raw samples, followed by a learnability-aware distillation mechanism that filters data based on RL training dynamics to ensure stable policy optimization. Furthermore, a code-based verifier provides high-precision reward signals for policy learning. The resulting dataset comprises 90k samples across 8 constraint categories and 14 task domains. Empirical evaluations demonstrate that MIFS-trained MLLMs achieve an average improvement of 8.13% on four MMIF benchmarks and a 3$\times$ faster training convergence compared to using raw data. Crucially, our approach mitigates the generalization trade-offs typical of SFT, preserving core visual capabilities while significantly boosting instruction-following precision.
Read the full abstract

All authors Yirong Zeng, Zhang Sai, Yuxian Wang, Yutai Hou, Yufei Liu, Xiao Ding, Bibo Cai

Computation and Language

State of Thought Enables Endogenous Reasoning

Zhiren Gong, Yikun Hou, Zihao Zeng et al. (+3 more)

Test-time compute has emerged as a major approach to improving the capabilities of Large Language Models (LLMs). However, existing test-time reasoning paradigms rely heavily on externally imposed control, either through fixed reasoning programs or through costly expansion in constrained search spaces, limiting both generalization and efficiency. We propose State of Thought (SoT), a new reasoning paradigm that enables endogenous reasoning in LLMs, with the model's internal reasoning state governing how reasoning unfolds. Concretely, SoT extracts a compact dynamics-geometric state from the model's internal information transfer and uses a 582-parameter controller on frozen backbones to selectively activate historical reasoning support useful under the current reasoning state, framing reasoning as a state-conditioned process over evidence rather than an externally prescribed token chain. Across quantitative (1.34x), general (1.62x), symbolic-and-code (1.76x), and long-context (2.51x) reasoning on 3 LLMs and 16 datasets, SoT consistently improves mean-baseline accuracy while reducing generated tokens by 62.6% and end-to-end latency by 44.6%. Across 2 VLM scales and 3 reasoning tasks, it improves mean accuracy by 3.8 points over reasoning baselines, with 74.9% fewer completion tokens and 73.5% lower latency than search-based methods. Under constrained access, SoT retains 38.2%/36.5% mean accuracy gains in training-free/embedding-only settings, while trajectory-only judging reaches 84.1% agreement across 3 API models. Together, endogenous state-driven reasoning provides a generalizable and efficient alternative.
Read the full abstract

All authors Zhiren Gong, Yikun Hou, Zihao Zeng, Ming Xiao, Chau Yuen, Wei Yang Bryan Lim

Computation and Language

Retrieval-Driven Memory Reconsolidation for Long-Term LLM Agents

Yuanyi Song, Yukai Wang, Xinbei Ma et al. (+7 more)

Long-term memory is essential for LLM-based agents operating over extended interactions. Existing memory systems primarily update memory when new information arrives, treating retrieval as the endpoint of memory access rather than a driver of memory evolution. Consequently, retrieval feedback is rarely exploited to reorganize memory for future access continuously. Moreover, most existing approaches rely on predefined memory structures together with fixed retrieval pipelines, limiting the agent's ability to organize and evolve its own memory autonomously. Inspired by memory reconsolidation in cognitive neuroscience, we propose REALM, a reconsolidation-evolution agentic long-term memory framework. It models long-term memory as a continual lifecycle by autonomously organizing memories into a heterogeneous cognitive graph, retrieving evidence via adaptively composed graph-search atoms, and continually reconsolidating memories based on retrieval feedback. REALM achieves an average accuracy of 75.97% on LoCoMo and 65.11% on LongMemEval, outperforming the strongest baselines by 7.17 and 1.31 points respectively. Ablation studies confirm that memory reconsolidation consistently boosts performance, with further analyses revealing that it progressively reorganizes related memory units into more coherent local structures for collective evidence recall and utilization during reasoning. These results suggest that retrieval-driven memory reconsolidation provides an effective mechanism for continually evolving long-term memory in LLM agents.
Read the full abstract

All authors Yuanyi Song, Yukai Wang, Xinbei Ma, Zhihui Fu, Jianghao Lin, Weiwen Liu, Jun Wang, Huarong Deng, Yong Yu, Weinan Zhang

Computation and Language · Cross-listed from cs.AI

Self-Orchestrating Language Models: Leveraging Semantic Dependence for Efficient Inference

Tian Jin

Large language models (LLMs) demonstrate impressive capabilities, but their deployment presents significant efficiency challenges. Autoregressive decoding imposes substantial inference latency and under-utilizes hardware accelerators in low batch size regimes. Discrete diffusion models can generate in parallel but struggle to match autoregressive quality without many diffusion denoising steps. Long-context reasoning creates memory bottlenecks that strain even state-of-the-art accelerators. My thesis is that language models can direct their own inference execution strategy by annotating semantic dependence – which tokens depend on which others – in their generation. I call such models self-orchestrating language models. For each system, I design a runtime that acts on these annotations to parallelize autoregressive decoding, evict intermediate context, or derive denoising orders, achieving Pareto-optimal quality-efficiency trade-offs. I demonstrate this approach through three self-orchestrating systems. First, PASTA uses semantic dependence to parallelize autoregressive decoding, training the model to annotate which output chunks can generate independently. Second, TIP uses semantic dependence to evict intermediate reasoning steps from the KV cache, reducing memory consumption while preserving accuracy. Third, Planned Diffusion uses semantic dependence to derive a denoising order for discrete diffusion, autoregressively generating a plan that specifies which chunks to denoise in parallel.
Read the full abstract

Computation and Language · Cross-listed from cs.CY

LLMs as Oracles: Reliance on LLMs for Subjective Personal Questions

Myra Cheng, Lujain Ibrahim, Grace Liu et al. (+5 more)

We characterize how people are turning to LLMs as oracles: all-knowing authorities on subjective personal questions. Motivated by risks to users' autonomy and well-being, we develop a typology and LLM-based methods to measure this form of AI reliance at scale and understand how people are offloading judgment and decision-making to AI. Applying our typology to public usage data (68K prompts from WildChat and ThoughtTrace), we find that LLM-as-oracle use has increased over time (2023-2026) and is more prevalent among younger users. We further build a privacy-preserving data donation tool to analyze individuals' longitudinal usage data (140K prompts from 52 participants), identifying similar trends. People are often unaware of their own LLM-as-oracle use, and express dissatisfaction with this behavior after seeing our tool's analysis. Finally, we identify two drivers of LLM-as-oracle use: people's perceptions of AI and the behavior of AI models themselves, which motivate possible interventions to support users' self-deliberation.
Read the full abstract

All authors Myra Cheng, Lujain Ibrahim, Grace Liu, Michelle S. Lam, Vishakh Padmakumar, Nick Madibekov, Diyi Yang, Dan Jurafsky

Computation and Language

Enemray: Toward Capable Language Models for Hassaniya

Cheikh Ahmed

We introduce Enemray, a Hassaniya-centric language model that enables general-purpose interaction in Hassaniya. Enemray is trained around a stability–plasticity objective: acquire strong Hassaniya linguistic and cultural competence while preserving the general reasoning, multilingual, instruction-following, and safety behaviors of a capable instruction-tuned model. The development pipeline separates language acquisition from behavioral specialization. A separately assembled continual-pretraining corpus provides broad exposure to natural Hassaniya and Mauritanian text; layer-selective continual pretraining learns a compact language-specific parameter update; that update is transferred into the instruction-tuned parameter space; and supervised post-training develops conversational, cultural, literary, task-oriented, and cross-lingual behavior. The supervised corpus integrates selected public Hassaniya and Mauritanian resources with a substantially larger body of newly collected, reconstructed, curated, and constructed instruction data, while policy-generated replay provides a retention signal from the reference model's own behavior distribution. The resulting collection is substantially larger and broader in purpose than existing Hassaniya text resources. In evaluation, Enemray achieves the strongest English to Hassaniya translation among the compared open and proprietary models and the highest overall score on Mauritanian translation error detection, while retaining most of the general capabilities of its instruction-tuned base model on mathematical reasoning, knowledge, code generation, and function calling. This report describes the motivation, data construction, model design, training methodology, and evaluation of Enemray.
Read the full abstract

Computation and Language

Route, Don't Fix: Regime-Dependent Decoding Correction and a Trajectory-Gated Router for Reliable Clinical LLM Answer Selection

Zeyu Dong, Benjamin Wang and Joyee W. Jin

Large language models (LLMs) are often deemed unsafe for clinical question answering because of their tendency to hallucinate. Retrieval augmentation, fine-tuning, and external verifiers require new infrastructure that clinical governance must approve and may add latency or extra model calls. Inference-time correction uses the model's internal logit signals, but a fixed transformation need not suit every question. A corrector that improves accuracy by about ten percentage points on a truthfulness stress test yields negligible gains on clinical multiple-choice benchmarks, where instruction tuning concentrates output probability on one answer and leaves low terminal entropy. We introduce ALTAS, which reads terminal entropy and late-layer linearity ($R^2$) from one forward pass to choose per question between greedy decoding and late-layer trajectory correction. No classifier, probe, or head is trained; the router operates on candidate-answer logits and adds 6.5% latency overhead. Applied to every question, the correction improves TruthfulQA over greedy at 3B and 8B by 11.4 and 10.0 percentage points, respectively ($p<10^{-10}$). Gated per question, ALTAS retains gains of 8.3 to 9.5 percentage points while keeping MedQA, PubMedQA, and MedHallu within a one-percentage-point do-no-harm band, with no statistically significant differences from greedy. The method passes verification sweeps over frozen thresholds, the scoring rule, and the domain label.
Read the full abstract

Computation and Language

MedTRACE: Tool-Augmented Multimodal Clinical Reasoning Agents for Evidence-Grounded Decision-Making

Ji Lu, Lifei Liu, Haoran Yu et al. (+5 more)

Multimodal clinical decision-making requires reliable reasoning over heterogeneous evidence from electronic health records, medical images, and physiological signals. Existing models typically map these inputs directly to diagnoses without explicitly assessing evidence sufficiency, tool-use requirements, or diagnostic uncertainty. This paper presents MedTRACE, a tool-augmented multimodal clinical reasoning agent for evidence-grounded decision-making. MedTRACE uses modality-specific encoders to construct a unified patient-state representation and performs an iterative loop of hypothesis formation, toolaware deliberation, and evidence verification. It dynamically invokes visual grounding, evidence retrieval, and structured parsing tools to locate diagnosis-relevant regions, retrieve clinical knowledge and similar cases, and extract structured findings. The acquired evidence enters an evidence memory, where a consistency verifier confirms or revises the current hypothesis. MedTRACE outputs a diagnosis together with supporting evidence, an auditable reasoning trace, and calibrated confidence. Experiments on multiple multimodal clinical diagnosis benchmarks show that MedTRACE improves diagnostic accuracy by 5.4% and AUROC by 4.7 percentage points over the strongest baseline. It also improves evidenceselection F1 by 8.2 percentage points and visual-grounding IoU by 6.5 percentage points, reduces expected calibration error by 31.6%, and decreases unsupported diagnostic errors by 27.8%. These results demonstrate that active evidence acquisition and verification improve the accuracy, interpretability, and reliability of multimodal clinical decisionmaking.
Read the full abstract

All authors Ji Lu, Lifei Liu, Haoran Yu, Xianglong Wang, Yiru Fang, Kuo Yang, Huiran Duan, Jianping Gou

Computation and Language

A primer on evaluation methods for large language models in healthcare

Suzannah E McKinney, Phuc Vu, Samuel A Justice et al. (+10 more)

Large language models (LLMs) have a growing range of applications in medicine, and their evaluation is critical for ensuring they provide benefit and not harm. This evaluation can be more challenging than traditional machine learning for many reasons, including probabilistic and open-ended outputs, and behavior that shifts with prompt design and accumulated context. This review covers four key areas of LLM evaluation: principles of study design, statistical methods, capability evaluation and clinical application evaluation. Capability evaluation considers different benchmarks, including multiple-choice, agentic and multi-turn benchmarks, alongside operational metrics like token usage and latency. Clinical application evaluation addresses establishing accuracy of free text outputs, such as human review and LLM-as-a-judge, and clinical trial approaches. Across sections, we describe underlying concepts and potential pitfalls, while emphasizing the importance of aligning evaluation methods with the research question. Together, this article aims to provide a pragmatic basis for designing and executing rigorous evaluations of healthcare LLMs.
Read the full abstract

All authors Suzannah E McKinney, Phuc Vu, Samuel A Justice, Christopher Humphries, Alyssa Pradhan, Timothy J Keyes, Kameron C Black, John L Havlik, David JH Wu, Jack W O'Sullivan, Ethan Goh, Sarah F Mercaldo, James M Hillis

Computation and Language

Tone on a Budget: A Reference-Free Metric for Lexical Tone in Massively Multilingual Text-to-Speech

Moses Daudu, Adeola Enitan Bamidele and Honor-Jesus Bezaleel

In Yorùbá, pitch alone separates ọkọ (husband, Mid), ọk\dò (vehicle, Low), and ọk\dó (hoe, High) – the diacritics ARE the tone marks. Yet character error rate (CER), the standard automated metric for text-to-speech (TTS), is in practice computed from ASR output that drops those marks: a synthesizer can ace CER and still say vehicle for husband. We introduce DunDun – named for the dùndún, the Yorùbá talking drum that speaks through pitch alone – an automated, reference-free lexical-tone metric that needs no tone-labelled corpus. The gold High/Mid/Low sequence is read from the input text's diacritics (in TTS that text exists by construction, so no reference recording is needed); the prediction comes from the audio's pitch track. We validate three ways. Flattening pitch with PSOLA resynthesis collapses DunDun while CER does not move. Inverting High and Low in the answer key of 300 native recordings drives the two-class readout to 0.14, symmetrically below its 0.35 chance level – a consistency check on the scoring path, not independent evidence. And three native listeners, over 67 blind A/B trials, pick the tone-correct clip 89.6% of the time (95% CI 80.0-94.8; p < 1e-4); whether DunDun tracks those judgements trial by trial is not resolved at this sample size. Applied to a massively multilingual zero-shot TTS model, DunDun shows what CER cannot: Yorùbá tone sits near the native anchor before any Yorùbá fine-tuning (0.567 +/- 0.02 over five decode seeds vs. 0.596; chance 0.33), despite the 21.4% CER the model's own paper reports; and a few hours of clean audio halve CER (5.6% to 2.7% by 5h, 1.7% by 15h) while tone saturates within the hour. On non-tonal Swahili, CER already captures the gains: the metric a language needs is language-dependent. We release the metric and the complete validation protocol.
Read the full abstract

Computation and Language · Cross-listed from cs.AI

Crypto Accounting Bench: Evaluating Frontier and Open-Weight Models on Crypto-Asset Accounting Tasks

Kareem Khattab, Omar Khattab and Mohamed Ibrahem

We introduce Crypto Accounting Bench (CAB), a benchmark for assessing whether frontier and open-weight language models can reconstruct the complete journal entry that an organization actually posted for a crypto-asset transaction. CAB contains 118 evaluation tasks drawn from 7 pseudonymized organizations. Each task combines transaction mechanics, asset quantities and base-currency values, wallet and legal-entity context, counterparty evidence, related transaction legs, recurrence, tax-lot evidence, and the organization's complete chart of accounts. The target is a balanced structured entry with every required account, side, amount, currency, and full-precision asset quantity. We evaluate 12 models spanning proprietary frontier systems and open-weight releases over 3 independent attempts per task, producing 4,248 trajectories. We report 3 metrics: Mean Score, Best@3, and Pass@3. Pass@3 is the fraction of tasks with at least 1 of 3 attempts that satisfies every rubric criterion and required gate. The leading model reaches 77.43% Mean Score, while the best Pass@3 is 56.78%. Deterministic diagnostics, read from each task's best of 3 attempts and macro-averaged across the 12 models, show higher base-amount agreement (97.8%) than deciding-account accuracy (56.3%). Together with the failure analysis, these results identify account selection and complete-entry composition as the main remaining challenges on CAB.
Read the full abstract

Computation and Language

Mind Which Bird You Favour: Parameterizing Adequacy-Fluency Balance in Meta-Evaluation of Machine Translation

Behzad Shayegh and Niloofar Kazemi

There is a tradeoff in machine translation meta-evaluation between prioritizing alignment with adequacy versus fluency. The balance depends on the combination of translation systems in the meta-evaluation dataset. This system set is a small, filtered sample whose characteristics change heavily across years and language pairs; it does not represent the true system distribution. Consequently, the adequacy-fluency balance is often unrepresentative and subject to change. For sensitive domains, controlling this balance is critical. We expose this balance as a tunable choice. To achieve a target balance, we reweight existing systems while minimizing distortion from uniform weighting, ensuring the evaluated systems remain real and representative. We provide an exact optimization algorithm with theoretical guarantees and pruning mechanisms to compute these weights. To validate meta-evaluation internal consistency, we design a scorer-augmentation framework that establishes a known relative identity for the scorers. Results demonstrate that our reweighting method effectively controls the adequacy-fluency balance and preserves the internal consistency, outperforming prior approaches. Finally, we analyze the performance of popular scorers across a sweep of this parameter.
Read the full abstract

Computation and Language · Cross-listed from cs.RO

Language-Guided Representation Learning for Robust Cross-Sensor Material Recognition

Mashood M. Mohsan, Muhayy Ud Din, Binzhao Xu et al. (+2 more)

Robots need touch to manipulate objects safely and reliably, as many properties, such as softness, texture, and contact stability, are hard to infer from vision alone. However, vision-based tactile sensors yield different observations of the same material due to variations in optics, elastomer properties, and illumination, leading to poor generalization when trained on a single or multiple sensors. We propose a language-guided distillation framework for learning sensor-robust tactile representations. Language encodes high-level semantic properties of touch (e.g., rough, soft, slippery) that remain invariant across sensing hardware, providing a natural sensor-agnostic supervisory signal. We construct a 39K-sample touch-language dataset with human-annotated material labels and train a tactile encoder to align sensor-specific tactile images with language embeddings in a shared semantic space. We evaluate our approach for few-shot learning and cross-sensor transfer and benchmark it on six existing tactile datasets. Our method achieves 95% accuracy in the 100-shot setting, improves cross-sensor transfer by an average of 13.3% accuracy, and yields up to 19% accuracy gains across six existing tactile datasets. These results demonstrate that language-guided distillation enables scalable and hardware-agnostic tactile representation learning. Code and dataset are available at https://mashood3624.github.io/Language_Tactile/
Read the full abstract

All authors Mashood M. Mohsan, Muhayy Ud Din, Binzhao Xu, Ahmad Abubakar, Irfan Hussain

Computation and Language

Func-R1: Incentivizing Mathematical Function Reasoning in Multimodal Large Language Models

Mingze Yin, Xiaohan Wang, Dian Li et al. (+8 more)

Performing deliberate mathematical reasoning in visual contexts is a hallmark of advanced Multimodal Large Language Models (MLLMs) and requires a sophisticated synthesis of perceptual grounding and symbolic logic. However, in the realm of mathematical functions, our investigation reveals a critical modality interference phenomenon: even advanced models, while performing textual computational reasoning, tend to disregard or misinterpret essential visual cues. To address this challenge, we propose Func-R1, which synergistically harmonizes precise visual perception and rigorous logical reasoning. Concretely, built upon an explicitly decoupled architecture, we employ a hierarchical post-training framework to progressively identify critical visual evidence and conduct in-depth theoretical reasoning. Furthermore, the Perception-Aligned Theoretic Optimization (PATO) strategy is proposed to steer policy updating towards internalizing fundamental theoretical properties while dynamically rectifying heterogeneous visual information throughout the reasoning process. Extensive experiments across diverse benchmarks demonstrate that Func-R1 delivers the optimal performance among open-source MLLMs, even surpassing GPT-5 with an 8.4% improvement on MathVerse's function-oriented tasks.
Read the full abstract

All authors Mingze Yin, Xiaohan Wang, Dian Li, Haichao Yao, Yilin Zhao, Youjun Chen, Gang Liu, Jintai Chen, Yiheng Zhu, Chang-Yu Hsieh, Aimin Pan

Computation and Language

Pull: Lazy Materialization of Working Memory for Stateful LLM Conversations

Jiangang Chen

As LLM conversations grow to hundreds of turns, full-context injection incurs $O(N^2)$ cumulative token costs, while lossy summarization or hard truncation irreversibly discards historical state. We propose Pull, a session router that maintains an addressable metadata directory via a local, deterministic Purifier (zero LLM calls, millisecond-level latency). At query time, the LLM lazily materializes only the turns it needs; unmaterialized turns remain accessible but collapsed. Unlike irreversible compression, Pull's materialization is reversible; subsequent queries can expand any collapsed turn. On LoCoEval (128 conversations, 12,780 turns), Pull reduces per-query context tokens (Phase 2) by 75.1 percent on single-hop tasks with equivalent quality ($\Delta = -0.002$, n.s.) and by 72.0 percent on multi-hop tasks with no quality loss ($\Delta = +0.017$). A controlled routing benchmark (7,831 queries x 10 methods) shows that entity lifecycle tracking is empirically a prerequisite for distance-independent routing. On BEAM 1M (14 conversations, 263 questions), Pull improves F1 by +55.2 percent over a truncation baseline.
Read the full abstract

Computation and Language

How broad is that claim? Mapping Generalisation in NLP Research

Chenxin Diao, Nataliya Stepanova and Emily Allaway

Generalisations are common in scientific communication, even though they are semantically ambiguous. An automated method is needed to identify and categorise claims according to their level of generalisation, in order help detect an over-reliance on generalisations and possible misrepresentations of scientific findings. We introduce a comprehensive taxonomy of generalisations in the scientific domain, NLPGenX, which labels claims according to their level of generality and framing within the text. We operationalise this taxonomy with an LLM-powered framework, NLPGenA, that automatically classifies sentences from scientific articles into 5 different generalisation classes. We validate our framework with human annotators and use the framework to construct a large-scale dataset of NLP papers annotated according to generality, with auxiliary labels for hedging and vague descriptors (NLPGens). We use NLPGens to analyse the use of generalisations in NLP papers across multiple venues and subdomains, and to examine associations with citation counts, hedging, and vague descriptors.
Read the full abstract

Computation and Language · Cross-listed from cs.MA

Loop-Back Authority in LLM Agent Teams: A Paired Experiment on Flat and Hierarchical Coordination

Burak Agachan, Max van Duijn and Amirhossein Zohrehvand

Does authority in AI teams improve the outcome? Organizational theory asserts that authority facilitates decision making, improving quality. Meanwhile, some nascent AI research suggests that revision under authority makes LLM output worse. Multi-agent LLM frameworks default to giving a Manager agent the authority to send a worker's output back for revision. Prior comparisons test the effect of authority using verifiable tasks. We conduct an experiment on an open-ended task, business-intelligence reporting, using a sample of 43 paired laptop products and 86 runs. Each report is written once by a hierarchical team and once by a flat team. We find that flat teams produce higher-quality reports, scoring higher on Utility (d = 0.42, p = 0.009) and Writing Clarity (d = 0.34, p = 0.030). The reports are the same length, but hierarchical team reports use 53% more hedging words such as "may" and "could", and each revision is associated with a 0.14-point drop in Writing Clarity on a 1 to 5 scale. Before any revision, the hierarchical team's first draft is indistinguishable from the flat team's report. In other words, the quality gap can be traced to revision. Authority improves quality when the Manager can verify the work, else when it can only provide feedback it has a negative effect on quality.
Read the full abstract