News / #paper Tag Research papers 500 articles archived under #paper · RSS Sign in to follow arXiv — Machine Learning research 2d ago In-Context Learning for System Identification: Probabilistic Formulation, Long-Sequence Handling, and Benchmark Validation arXiv:2610.13411v1 Announce Type: new Abstract: Traditional system identification typically involves two steps: initially, training data is processed to estimate a model of the system of interest; then, the model is used to predict outputs for new input queries. In contrast,… 16 arXiv — Machine Learning research 2d ago PPG-Bench: A Unified Benchmark for PPG Foundation Models arXiv:2610.13435v1 Announce Type: new Abstract: Photoplethysmography (PPG) is increasingly recorded by wearable and clinical devices at enormous scale, and a growing number of PPG foundation models (FMs) have been developed to compute reusable representations for various… 27 arXiv — Machine Learning research 2d ago Beyond Temporal Proximity: Explanatory World Models for Credit Assignment in Reinforcement Learning arXiv:2610.13504v1 Announce Type: new Abstract: Generative Recommenders increasingly use Reinforcement Learning (RL) to optimize outcomes that may appear hundreds or thousands of interactions after a decision. Standard RL propagates reward according to temporal proximity rather… 5 arXiv — NLP / Computation & Language research 2d ago AutoIndexer: Flexible-Order Decoding by Training Causal Models on Chains of Edits arXiv:2610.12545v1 Announce Type: new Abstract: Autoregressive decoding is less suited to non-causally ordered data, e.g., cross-references or future dependencies, since their outputs cannot be revised post hoc, unlike iterative human reasoning. Diffusion LLMs partially mitigate… 33 arXiv — NLP / Computation & Language research 2d ago SWE-Duel: Towards a Self-Scaling Arena for Coding Agents arXiv:2610.12569v1 Announce Type: new Abstract: Static coding benchmarks are fixed at release. Over time their tasks leak into training data, and stronger agents eventually saturate them. We argue that a benchmark should instead aim to be self-scaling: its tasks and oracles are… 19 arXiv — NLP / Computation & Language research 2d ago Contextual Correction of Parallel Draftsfor Speculative Decoding arXiv:2610.12570v1 Announce Type: new Abstract: Speculative decoding accelerates large language model inference by using a lightweight drafter to propose multiple tokens that are subsequently verified in parallel by the target model. Recent diffusion-based drafters make this… 33 arXiv — NLP / Computation & Language research 2d ago CLUE: A Contrastive Learning Framework for Unsupervised Event Type Induction and Annotation arXiv:2610.12580v1 Announce Type: new Abstract: Event ontology is the foundational framework for defining events in a dataset. Event type induction generally involves domain experts who define guidelines for creating event types and their names based on the dataset's domain and… 29 arXiv — NLP / Computation & Language research 2d ago One Model to Loop Them All: Elastic Latent Recurrence for Language Models arXiv:2610.12582v1 Announce Type: new Abstract: A latent recurrent language model applies a shared block of layers repeatedly, so one checkpoint can trade inference compute for accuracy by changing the loop count. At one loop, however, such models typically fall well short of a… 25 arXiv — NLP / Computation & Language research 2d ago Reflective Prompt Optimization of a Deep-Research Agent: A Topic-Disjoint, Multi-Seed Protocol for Measuring Transferable Gains and Prompt-Level Overfitting arXiv:2610.12601v1 Announce Type: new Abstract: Prompt optimization is an attractive alternative to reinforcement learning for adapting language-model agents, since it is cheap and produces human-readable artifacts. On factual tasks, however, it carries a failure mode that… 27 arXiv — NLP / Computation & Language research 2d ago Self-Preservation in Language Models arXiv:2610.12602v1 Announce Type: new Abstract: Continual learning (CL) seeks to adapt pretrained models while preserving prior capabilities. Yet the tasks supplied for preservation cover only part of what a model knows, while forgetting can extend beyond them. Recent work shows… 14 arXiv — NLP / Computation & Language research 2d ago GeopoliticalQA: Benchmarking Retrieval and Generation over Intelligence Reports arXiv:2610.12617v1 Announce Type: new Abstract: Geopolitical and strategic intelligence reports constitute a rich source of expert knowledge and have increasing value in the current political climate, but their heterogeneity and analytical complexity pose challenges for… 35 arXiv — NLP / Computation & Language research 2d ago perturber: A Stateless Service for Semantics-Preserving Text Perturbations arXiv:2610.12667v1 Announce Type: new Abstract: Large language model (LLM) evaluations on clean benchmarks overstate model robustness: real inputs arrive perturbed, and these meaning-preserving variants routinely move model answers. Studying this systematically requires applying… 21 arXiv — NLP / Computation & Language research 2d ago GeoFitBench-LLM: A Benchmark for Assessing Large Language Models' Capabilities in Geospatial Data Requirements Elicitation for Geo-Analytic Tasks arXiv:2610.12669v1 Announce Type: new Abstract: Large language models are becoming central to GeoAI systems, yet their evaluation rarely considers the elicitation of geospatial data requirements. This omission is critical as retrieval oriented geo-analytic tasks cannot be… 19 arXiv — NLP / Computation & Language research 2d ago Activating the Annotator: Operationalising Lived Experience in Data Annotation arXiv:2610.12701v1 Announce Type: new Abstract: Perspectivist NLP has established that annotator positionality shapes labels for subjective tasks, but the field still lacks methods for operationalising it. Positionality is typically operationalised as a demographic form… 20 arXiv — NLP / Computation & Language research 2d ago Unsupervised Multimodal Reward Modeling arXiv:2610.12707v1 Announce Type: new Abstract: Vision-language reward models are trained on annotated preference pairs, which are expensive to collect, can disagree, and are ranked by benchmark accuracy. We build one with no human preference label: a linear head on an… 22 arXiv — NLP / Computation & Language research 2d ago U4RASD at KnowledgeGraphEval-2026: Ontology-Constrained Encoder and LLM Systems for Arabic Relation Extraction arXiv:2610.12742v1 Announce Type: new Abstract: This paper details our submission to KnowledgeGraphEval 2026 Subtask 2 on directed Arabic relation extraction. We explored encoder-based and large language model approaches for predicting one of 40 relations or no_relation from an… 5 arXiv — NLP / Computation & Language research 2d ago MADS: Multi-Agent Dialog Simulation for Robust Conversational Agents arXiv:2610.12757v1 Announce Type: new Abstract: Task-oriented conversational agents remain fragile under realistic conditions, especially when users exhibit non-cooperative behavior. Existing function-calling benchmarks underrepresent adversarial conversation trajectories,… 4 arXiv — NLP / Computation & Language research 2d ago DistressBench: Evaluating Multi-Dimensional Crisis Support in Large Language Models arXiv:2610.12758v1 Announce Type: new Abstract: Language models have been adopted faster than evaluation practices that reliably assess their risks, and a growing share of use is affective rather than informational. Within that traffic users disclose suicide and self-harm (SSH)… 24 arXiv — NLP / Computation & Language research 2d ago People Making Conversation: Evaluating How Naturally Speech Models Converse arXiv:2610.12802v1 Announce Type: new Abstract: A conversational speech model has to decide, at every pause, whether to speak. Existing evaluations test boundary detection, policy adherence, or aggregate statistics, not this decision. We place real-time speech systems at 427… 6 arXiv — NLP / Computation & Language research 2d ago When Charts Deceive Web Agents: A Paired Benchmark for Misleading Visualization-Grounded Tasks arXiv:2610.12823v1 Announce Type: new Abstract: Web agents increasingly browse, interpret, and act on web content on behalf of users. In many realistic workflows, however, the visual evidence they consume is not neutral: charts and dashboards can be misleading, shaping judgments… 18 arXiv — NLP / Computation & Language research 2d ago COFFEQA: Counterfactual-Guided Few-Shot Distillation for LLM Question Answering arXiv:2610.12837v1 Announce Type: new Abstract: Knowledge distillation aims to train a smaller student model to mimic a larger teacher model for resource-constrained environments. However, the process of distillation is typically data-intensive and computationally expensive,… 11 arXiv — NLP / Computation & Language research 2d ago Fear Is Not Always Fear: Variation in Emotion Label Equivalence Across Datasets arXiv:2610.12841v1 Announce Type: new Abstract: Emotion classifiers are routinely applied beyond their training data, on the assumption that same-named labels such as fear or surprise mean the same thing across resources. We test this assumption for five labels shared by… 37 arXiv — NLP / Computation & Language research 2d ago Unreliable Narrator Framing as a Cost-effective Mechanism for Satire Explanation of Australian and American Satirical News arXiv:2610.12863v1 Announce Type: new Abstract: Satirical news is a unique form of misinformation: it is intended to be humorous by the original publication source but can be misinterpreted. Explanation of satirical news articles is challenging because recent and local context… 30 arXiv — NLP / Computation & Language research 2d ago Time Delay System for Sequence Modeling arXiv:2610.12864v1 Announce Type: new Abstract: Existing sequence models share a critical limitation: they lack an explicit, interpretable mechanism for content-aware temporal recall. LSTMs compress everything into a single hidden state, thereby losing information about specific… 27 arXiv — NLP / Computation & Language research 2d ago Temporal Evidence Forests for Long-Horizon Multi-Party Conversational Memory arXiv:2610.12874v1 Announce Type: new Abstract: Long-term memory has been widely adopted in LLM-based agents to support persistent interaction and personalized assistance. Long-term multi-party interactions, however, accumulate substantially more detailed information, with… 36 arXiv — NLP / Computation & Language research 2d ago Rethinking the Roles of Diffusion and Decoding: Predictive-State Flows for Parallel Language Generation arXiv:2610.12898v1 Announce Type: new Abstract: In continuous diffusion language models (DLMs), latents generated by the diffusion prior are mapped almost deterministically to tokens, either by a decoder or through a token embedding matrix. Unlike in image generation, where… 5 arXiv — NLP / Computation & Language research 2d ago SEEDS: Preview-Guided Evidence Admission for Search Agents arXiv:2610.12932v1 Announce Type: new Abstract: Search agents extend large reasoning models with multi-round access to external knowledge, yet most existing systems largely conflate retrieving evidence with consuming it. Retrieved documents are commonly incorporated according to… 37 arXiv — NLP / Computation & Language research 2d ago Surfing the Activation Wave: Analyzing the Information and Geometry of LLM Hidden States for Speculative Decoding arXiv:2610.12939v1 Announce Type: new Abstract: Decoder hidden states from different layers of large language models (LLMs) often encode complementary information. However, existing speculative decoding methods typically rely on a small set of target-model layers chosen using… 10 arXiv — NLP / Computation & Language research 2d ago Forecasting Corpus-Sampling Disagreement in Masked Text Reconstruction arXiv:2610.12987v1 Announce Type: new Abstract: If a second text corpus were collected from the same population, how much would a predictor's outputs change? We study this question for masked-text reconstruction using a smoothed predictor built from nearby token-pair counts and… 15 arXiv — NLP / Computation & Language research 2d ago Language Models Have Interpretable Narrative Mechanisms arXiv:2610.12989v1 Announce Type: new Abstract: We investigate whether language models contain internal components that contribute to representing narrativity, the degree to which a text exhibits narrative properties. Across GPT-2-Small, Gemma-2-2B, and Llama-3.1-8B, we identify… 33 arXiv — NLP / Computation & Language research 2d ago What Should SFT Learn? Conditional Information Gain for Generalizable Post-Training arXiv:2610.12995v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) remains a widely used approach for post-training large language models, because fixed demonstrations can directly introduce desired reasoning strategies and behavioral patterns. Yet forcing a model to… 31 arXiv — NLP / Computation & Language research 2d ago Evaluating LLM Creativity through Long-Tail Performance arXiv:2610.12998v1 Announce Type: new Abstract: Creativity benchmarks for large language models (LLMs) vary widely in task and metric design. This raises the question of whether they capture a common notion of creativity. We propose that this shared target can be formalized as… 14 arXiv — NLP / Computation & Language research 2d ago Evo$^2$: Evolving the Evolver through Weight-Harness Co-Evolution arXiv:2610.13025v1 Announce Type: new Abstract: Self-evolving agents are increasingly used to improve language model systems without human intervention through either weight updates or harness improvements. Existing approaches typically pursue these directions separately: some… 31 arXiv — NLP / Computation & Language research 2d ago RAMP: Recurrent Adaptive Mixed Precision for Efficient Prefill in Recurrent-Depth Language Models arXiv:2610.13041v1 Announce Type: new Abstract: Recurrent-depth language models improve inference-time reasoning by repeatedly applying a shared network to refine internal representations, but the additional recurrent computation also increases inference cost. This overhead is… 33 arXiv — NLP / Computation & Language research 2d ago CoBe: A Benchmark For Conversational Counterfactual Text Editing arXiv:2610.13057v1 Announce Type: new Abstract: Counterfactual text editing is the ability to revise a given text in light of a hypothetical change while preserving facts not causally affected by that change. When asked what would have happened if a doctor had not recommended… 32 arXiv — NLP / Computation & Language research 2d ago CliQ-RRG: Clinical-Knowledge Guided Disease-aware Visual-Textual Alignment for QA-Style Radiology Report Generation arXiv:2610.13059v1 Announce Type: new Abstract: Radiology reports are essential for diagnostic reasoning and patient care, yet their manual preparation is time-consuming and cognitively demanding. Automatic radiology report generation (RRG) offers a scalable alternative, but… 15 arXiv — NLP / Computation & Language research 2d ago KV-Repurpose: A Testbed for Evaluating Non-Prefix KV-Cache Reuse arXiv:2610.13060v1 Announce Type: new Abstract: KV-cache reuse in large language model serving is commonly limited to exact prompt prefixes, preventing reuse when the same retrieved document appears after different system prompts, conversation histories, or dynamic metadata. We… 6 arXiv — NLP / Computation & Language research 2d ago From 2.1M Hours of Raw Broadcast Audio to Finnish Speech SSL: Confidence Filtering and Architectural Analysis at Scale arXiv:2610.13102v1 Announce Type: new Abstract: Broadcast archives offer scale and diversity for self-supervised learning (SSL) but contain substantial noisy, non-speech, and multilingual content. Prior work typically relies on voice activity detection or language identification… 9 arXiv — NLP / Computation & Language research 2d ago BenCoDiC: A Large-Scale Contextual Cyberbullying Corpus for Bengali Political News Discourse FULL VERSION arXiv:2610.13121v1 Announce Type: new Abstract: Cyberbullying is a growing concern in online communities, yet existing Bengali corpora remain limited in contextual information, annotation transparency, scale, accessibility, and support for multidimensional analysis, thereby… 31 arXiv — NLP / Computation & Language research 2d ago Neurograf v1: An End-to-End Romanian-First Language Model Family arXiv:2610.13134v1 Announce Type: new Abstract: We present Neurograf v1, an experimental end-to-end Romanian-first language-model pipeline developed to investigate the feasibility of training language models from scratch for a lower-resource European language. The pipeline… 38 arXiv — NLP / Computation & Language research 2d ago SOAR: Source-Aware Reinforcement Learning with Precise Credit Assignment for Search Agents arXiv:2610.13157v1 Announce Type: new Abstract: Reinforcement learning (RL) for search agents often suffers from evidence fabrication, a failure mode where agents bypass external information ($E_{ext}$) and fabricate an incorrect answer. We argue that this fabrication arises… 28 arXiv — NLP / Computation & Language research 2d ago Scaling Agentic Data for Long-Horizon Terminal Intelligence arXiv:2610.13166v1 Announce Type: new Abstract: Terminal agents are moving beyond local operations toward completing real-world professional tasks. Short trajectories can demonstrate commands and tool calls, but they do not fully show how agents accumulate evidence through… 14 arXiv — NLP / Computation & Language research 2d ago PreSTO: Predictive Subtree Prefetching for Fast LLM Power Sampling arXiv:2610.13171v1 Announce Type: new Abstract: Power sampling improves large language model (LLM) reasoning at test time by sampling from a sharpened version of the base model's distribution. Its sampler, PowerMH, is slow because its Metropolis--Hastings (MH) updates are… 14 arXiv — NLP / Computation & Language research 2d ago SharP: Soft and Hard Prompt-Guided Augmentation with LLM for Low Resource Fake News Detection arXiv:2610.13207v1 Announce Type: new Abstract: Fake news detection under low resource conditions is challenged by the scarcity of labeled data and the difficulty of capturing subtle deceptive patterns. In this work, we focus on low resource fake news detection, where only a… 6 arXiv — NLP / Computation & Language research 2d ago How Reliable are AMR Parser Outputs? Uncertainty Estimation for AMR Parsing arXiv:2610.13236v1 Announce Type: new Abstract: Recent advances have significantly improved the performance of Abstract Meaning Representation (AMR) parsers, yet determining when their outputs can be trusted remains largely unexplored. This work presents the first study of… 22 arXiv — NLP / Computation & Language research 2d ago Do Prompt Optimizers Break Requirements They Are Not Scored On? A Preregistered Study arXiv:2610.13287v1 Announce Type: new Abstract: Prompt optimizers rewrite a prompt to raise one target metric, but prompts also state requirements the metric does not score, such as an output format, citations, or abstention. In a preregistered study, we run GEPA, MIPROv2, and… 15 arXiv — NLP / Computation & Language research 2d ago Agreement Without Alignment: Label-Free Rubric Clarification Increases LLM-Judge Consensus but Not Agreement with Humans arXiv:2610.13303v1 Announce Type: new Abstract: LLM judges are increasingly deployed as panels, and disagreement among panel members is often read as a symptom of an unclear rubric. We test a label-free procedure that turns this disagreement into rubric repairs. The procedure… 9 arXiv — NLP / Computation & Language research 2d ago Host-Aware Web Crawling for LLM Pretraining Data arXiv:2610.13321v1 Announce Type: new Abstract: Web crawling is a major source of large language model (LLM) pretraining data, yet data-selection pipelines discard a large share of crawled pages. We investigate how a crawler should allocate its budget across and within hosts to… 17 arXiv — NLP / Computation & Language research 2d ago Test-Time Memory Construction arXiv:2610.13348v1 Announce Type: new Abstract: Large Language Models (LLMs) struggle to answer questions over long interaction histories, where relevant evidence may be scattered across distant sessions. Existing memory systems typically construct and maintain sophisticated… 7 arXiv — NLP / Computation & Language research 2d ago Overcoming Data Imbalances with Expert Selection Biases arXiv:2610.13370v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models have become the standard architecture for frontier LLMs. The multiple parallel experts in each transformer block theoretically enable expert specialization according to categories such as domains,… 19 Page 3 of 10 · 500 articles ← Newer Older →
