News / #paper Tag Research papers 500 articles archived under #paper · RSS Sign in to follow arXiv — NLP / Computation & Language research 3d ago A Primer on Computational Semantics for Artificial Intelligence Systems arXiv:2608.25022v1 Announce Type: new Abstract: As people adopt transformer-based language models (e.g., ChatGPT and Gemini) for an increasing number of use-cases, it is important to know how such models learn and represent the meaning of the language, and to be more informed… 38 arXiv — NLP / Computation & Language research 3d ago Behind the [MASK]: Disentangling Representation and Faithfulness in DAPF-Based Dementia Detection arXiv:2608.25028v1 Announce Type: new Abstract: Spoken-language analysis via prompt-based domain-adaptive models is a promising direction for low-resource, non-invasive dementia screening, but such models remain internally opaque. We study the interpretability of the… 6 arXiv — NLP / Computation & Language research 3d ago Padamitra: Grounded Glossary Generation for Classical Sanskrit arXiv:2608.25038v1 Announce Type: new Abstract: We introduce grounded glossary generation, a structured task requiring models to recover semantically meaningful Sanskrit phrases and produce translation-grounded meanings from a sloka-translation pair, formalizing the traditional… 8 arXiv — NLP / Computation & Language research 3d ago DataKernelBench: Can LLMs Optimize Database Queries on GPUs? arXiv:2608.25061v1 Announce Type: new Abstract: GPUs increasingly accelerate database systems, but query-specific peak performance still often relies on hand-written kernels. Existing LLM kernel benchmarks focus on machine learning operators, leaving irregular, heterogeneous,… 11 arXiv — NLP / Computation & Language research 3d ago HealthBench-Psych: A Mental Health Subset of OpenAI's HealthBench arXiv:2608.25071v1 Announce Type: new Abstract: General-purpose health benchmarks increasingly anchor claims about LLM medical performance, but they are not always resolved by clinical specialty, making domain-specific performance hard to isolate. Mental health is of acute… 17 arXiv — NLP / Computation & Language research 3d ago MTDiag: A Multi-Turn Diagnostic Dataset Towards Clinically Meaningful LLM Evaluation arXiv:2608.25085v1 Announce Type: new Abstract: Clinical diagnosis is fundamentally interactive and incremental, yet the dominant paradigm for evaluating Large Language Models (LLMs) in medicine remains static QA benchmarks or template-based dialogues. These benchmarks say… 38 arXiv — NLP / Computation & Language research 3d ago Apples to Apples? Towards Comparable Crosslingual Language Model Evaluation arXiv:2608.25089v1 Announce Type: new Abstract: Crosslingual evaluation of language models that enables fair comparisons remains a fundamental challenge in multilingual NLP. Existing studies adopt a variety of downstream tasks and intrinsic metrics with different theoretical… 17 arXiv — NLP / Computation & Language research 3d ago Less can be More: Relieving RAG Bottlenecks via Evidence Frontloading and Pressure-Adaptive Budgeting arXiv:2608.25115v1 Announce Type: new Abstract: Existing methods for improving Retrieval-Augmented Generation (RAG) efficiency mainly optimize downstream LLM generation, such as context compression or serving optimization. However, RAG is an end-to-end system, and its bottleneck… 29 arXiv — NLP / Computation & Language research 3d ago SelfGraphRAG: Bridging the Supervision Gap in Graph-Based RAG with Synthetic QA Generation arXiv:2608.25123v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) improves large language models by incorporating external knowledge without retraining, but existing methods often underuse the relational structure encoded in knowledge graphs. Graph-based RAG… 24 arXiv — NLP / Computation & Language research 3d ago Belief Cascades Drive Persuasion in LLM Agent Networks arXiv:2608.25152v1 Announce Type: new Abstract: Multi-agent LLM systems increasingly debate answers, coordinate research, simulate users, and mediate information flows, making agent-to-agent persuasion a basic but undermeasured capability. We introduce a controlled testbed for… 28 arXiv — NLP / Computation & Language research 3d ago The Changing Geometry of Grammar: Dimensionality and Neighborhood Reorganization across Transformer Layers arXiv:2608.25166v1 Announce Type: new Abstract: Transformer representations describe trajectories through high-dimensional vector spaces, which are shaped dynamically as tokens incorporate relational context across layers. Such data tend to concentrate on lower-dimensional… 5 arXiv — NLP / Computation & Language research 3d ago BanglaMamba: Exploring State Space Models for Bangla Fake News Detection arXiv:2608.25190v1 Announce Type: new Abstract: Fake news detection has become an important Natural Language Processing (NLP) task due to the rapid spread of misinformation through online news platforms and social media. While transformer-based models such as BanglaBERT achieve… 21 arXiv — NLP / Computation & Language research 3d ago From Memorization to Absorption: Mixed-Policy RL for Continual Knowledge Injection arXiv:2608.25243v1 Announce Type: new Abstract: Continual knowledge injection is essential for keeping large language models up-to-date in a fast-evolving world. Existing methods rely on supervised fine-tuning (SFT), which memorizes injected facts in their training format but… 23 arXiv — NLP / Computation & Language research 3d ago Groundhog Bit-Flip Attack: Seeding Infinite Generation Loops in Mixture-of-Experts LLMs through Bit Flips arXiv:2608.25276v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures enable scalable and efficient large language models (LLMs) by selectively activating expert sub-networks through a routing mechanism. However, this adaptive design introduces a new attack… 22 arXiv — NLP / Computation & Language research 3d ago Routed Graph Handoff: Adaptive Format Selection for Multi-Agent LLM Delegation arXiv:2608.25277v1 Announce Type: new Abstract: Multi-agent LLM systems coordinate through natural-language messages that consume 40--60\% of their token budget. Replacing these with structured graphs reduces cost but fails on tasks requiring adaptive reasoning. We propose… 20 arXiv — NLP / Computation & Language research 3d ago Provenance Before Prose: Claim-Locked Reporting arXiv:2608.25336v1 Announce Type: new Abstract: Large language models (LLMs) can fluently verbalize statistical evidence, yet statistical reports can still drift numerical values, invert effect directions, or restate thresholded contrasts as categorical effects. We frame these… 32 arXiv — NLP / Computation & Language research 3d ago GUIDE: Generative Unsupervised Chinese Query Correction via Phonetic and Visual Shared-ID Encoding arXiv:2608.25343v1 Announce Type: new Abstract: Chinese query correction (CQC) is important for search and query recommendation on content platforms, but supervised methods rely on large annotated correction pairs that are costly to maintain as query vocabularies evolve.… 34 arXiv — NLP / Computation & Language research 3d ago Short Horizons and Sparse Concepts: a Mathematical View of the Readout in the J-lens arXiv:2608.25347v1 Announce Type: new Abstract: The Jacobian lens (J-lens) has been proposed as a way to read verbalizable representations from language models. However, its principle and meaning lack a detailed and theoretical discussion. We provide a mathematical view of this… 31 arXiv — NLP / Computation & Language research 3d ago Leveraging Speech Acts for Low-Data and Cross-Domain Conversation Derailment Forecasting arXiv:2608.25359v1 Announce Type: new Abstract: Conversational derailment forecasting aims to predict when online discussions will escalate into hostility, enabling proactive moderation. Existing approaches often struggle in low-data settings and to generalize across domains.… 30 arXiv — NLP / Computation & Language research 3d ago Adaptive Triggering for Bias Correction in LLM Reasoning arXiv:2608.25379v1 Announce Type: new Abstract: Chain-of-thought prompting can expose and amplify demographic stereotypes within an LLM's intermediate reasoning and create a failure mode that final-answer debiasing alone cannot address. Mitigating such bias during generation… 11 arXiv — NLP / Computation & Language research 3d ago OmniPhys: A Unified Multimodal Benchmark for Physics Understanding and Generation from Chinese Educational Corpora arXiv:2608.25398v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong abilities in solving diverse visual and textual reasoning tasks. However, their development in the physics domain is significantly hindered by the lack of a… 37 arXiv — NLP / Computation & Language research 3d ago DCGC: Draft-Conditioned Global Correction for Complex Reasoning with Masked Diffusion Models arXiv:2608.25428v1 Announce Type: new Abstract: Correcting flawed reasoning traces remains a significant challenge for Large Language Models (LLMs), whose autoregressive generation can propagate early mistakes into subsequent reasoning. We introduce DCGC, a Masked Diffusion… 15 arXiv — NLP / Computation & Language research 3d ago MathAdv: What Theorem Provers Know, Reason, Formalize, and Generalize arXiv:2608.25449v1 Announce Type: new Abstract: Formal theorem proving enables machine-verifiable evaluation of mathematical reasoning, yet existing benchmarks often emphasize aggregate proof accuracy, concentrate on a narrow range of mathematics, and provide limited evidence of… 5 arXiv — NLP / Computation & Language research 3d ago VietAIDetector: An Open-Source Zero-Shot Detector for Vietnamese AI-Generated Text arXiv:2608.25478v1 Announce Type: new Abstract: In recent years, distinguishing between AI-generated text and human-written text has remained a challenge. In this paper, we introduce VietAIDetector, an open-source tool designed specifically for detecting Vietnamese AI-generated… 35 arXiv — NLP / Computation & Language research 3d ago ReliableRAG: Combating Misinformation in Retrieval-Augmented Generation via Reliability-Guided Reasoning Chains arXiv:2608.25487v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) has emerged as a powerful architecture for Question Answering (QA) by integrating external information into Large Language Models (LLMs). However, false, inaccurate, and misleading information… 23 arXiv — NLP / Computation & Language research 3d ago TOPAS: Workflow-Aware Prefix-State Scheduling for Multi-Agent LLM Serving arXiv:2608.25523v1 Announce Type: new Abstract: Prefix caching introduces a fundamental tradeoff in multi-agent large language model (LLM) serving: retaining a long system-prompt key-value (KV) cache for an agent accelerates future calls, yet it reduces the GPU memory available… 5 arXiv — NLP / Computation & Language research 3d ago ClueWeaver: Reward-Guided Dual-Agent Evidence Reasoning for Compact LLMs on Literary Long Narratives arXiv:2608.25531v1 Announce Type: new Abstract: Humanities and social science research requires close reading of long narrative materials such as novels, scripts, archives, and case reports, yet many users have limited access to costly proprietary long-context models. Compact,… 29 arXiv — NLP / Computation & Language research 3d ago Virgil: Navigating Explainability for Transformer-based Language Models arXiv:2608.25555v1 Announce Type: new Abstract: Explainability for transformer-based language models is becoming crucial as these systems are deployed in high-stakes applications. As a result, the ecosystem of explainability tools is rapidly evolving, becoming richer, but also… 29 arXiv — NLP / Computation & Language research 3d ago EgoArgus: Benchmarking VLMs as Situational Assistants for Modality-Grounded User Supports arXiv:2608.25561v1 Announce Type: new Abstract: VLMs are increasingly positioned as daily assistants that perceive first-person environments, follow user dialogue, and decide how to help. Existing egocentric benchmarks mainly evaluate visual understanding in isolation, leaving… 27 arXiv — NLP / Computation & Language research 3d ago Controllable Affective Generation via Latent Vector Steering arXiv:2608.25569v1 Announce Type: new Abstract: Large Language Models (LLMs) often produce emotionally flattened responses after alignment, limiting their effectiveness in affect-sensitive applications. In this paper, we propose EmoVec, a lightweight framework for controllable… 20 arXiv — NLP / Computation & Language research 3d ago Generative vs. Encoder Large Language Models for ASR Evaluation: A Comparative Study arXiv:2608.25574v1 Announce Type: new Abstract: Automatic Speech Recognition (ASR) is typically evaluated using Word Error Rate (WER), which poorly reflects semantic similarity. While embedding-based metrics correlate better with human judgments, the respective roles of encoder… 23 arXiv — NLP / Computation & Language research 3d ago Cross-Dataset Stability of Expert-Informed Skill Prompting and Fine-Tuning for Chinese Metaphor Identification arXiv:2608.25579v1 Announce Type: new Abstract: Metaphor-identification performance can change markedly across datasets that differ in text distribution and annotation policy. We examine whether a fixed expert-informed procedure produces a more even cross-dataset profile than… 7 arXiv — NLP / Computation & Language research 3d ago GRIP: Granular Reward-Guided Parameter Interpolation for Efficient Reasoning arXiv:2608.25583v1 Announce Type: new Abstract: Reasoning-oriented large language models often achieve strong problem-solving performance by generating long chains of thought, but this behavior substantially increases inference cost and latency. In contrast, instruction-tuned… 13 arXiv — NLP / Computation & Language research 3d ago JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution arXiv:2608.25593v1 Announce Type: new Abstract: Agent capability is not determined by the model alone. The agent harness, encompassing memory management, planning strategy, action protocol, and tool/skill orchestration, can dominate the contribution of the underlying foundation… 13 arXiv — NLP / Computation & Language research 3d ago From Specialization to Generalization: Instruction-tuned LLMs for Robust Harmful Content Mitigation arXiv:2608.25605v1 Announce Type: new Abstract: Large language models (LLMs) demonstrate impressive performance across a wide range of general NLP tasks; however, their effectiveness in sensitive domains, such as hate speech detection, remains less clear. Prior studies comparing… 25 arXiv — NLP / Computation & Language research 3d ago AWM: Answerable Working Memory for Long-Document VQA Agents arXiv:2608.25618v1 Announce Type: new Abstract: Long-document visual question answering increasingly relies on VLM agents that retrieve candidate pages, inspect page images, write findings to working memory, and synthesize answers. Working memory should carry answer-supporting… 24 arXiv — NLP / Computation & Language research 3d ago AutoVerifier: Residual-Guided Non-Parametric Optimization for Reference-Based Answer Verification arXiv:2608.25637v1 Announce Type: new Abstract: Reference-based verifiers are important for evaluating reasoning models and providing accurate outcome rewards in reinforcement learning with verifiable rewards. To improve verification accuracy, prior work has explored rule-based,… 20 arXiv — NLP / Computation & Language research 3d ago Unmatched Does Not Mean False: Incomplete Reference Sets Can Reverse Calibration Rankings in Open-Ended Theory-of-Mind Tracking arXiv:2608.25654v1 Announce Type: new Abstract: Open-ended Theory-of-Mind (ToM) trackers emit valid beliefs absent from finite references. A finite-reference-plus-matcher pipeline marks unmatched outputs false, creating proxy labels that can reverse proper-score model selection… 23 arXiv — NLP / Computation & Language research 3d ago Reconstructing the Right Episode: Evaluating Interleaved Conversational Memory Beyond Long Context arXiv:2608.25655v1 Announce Type: new Abstract: Conversations with chat assistants increasingly span many topics in a single long-running thread, challenging memory systems. Existing long-context and memory benchmarks often expose session or topic boundaries, or probe direct… 25 arXiv — NLP / Computation & Language research 3d ago Think-Probe-Respond: Improving Large Language Models as Judges of Research Idea Novelty arXiv:2608.25660v1 Announce Type: new Abstract: Automated novelty judgment can accelerate scientific discovery by enabling efficient evaluation, refinement, and comparison of research ideas. While large language models are increasingly adopted for this task, we investigate a… 17 arXiv — NLP / Computation & Language research 3d ago Overview of SHROOM-Visions 2026: A Shared Task on Hallucination Detection in Large Vision-Language Models arXiv:2608.25662v1 Announce Type: new Abstract: In 2026, we held the fourth iteration of the SHROOM Shared Task series: SHROOM-Visions (\textbf{S}hared-task on \textbf{H}allucinations and \textbf{R}elated \textbf{O}bservable \textbf{O}vergeneration \textbf{M}istakes in… 35 arXiv — NLP / Computation & Language research 3d ago Learning New Facts with QLoRA: An Acquisition-Retention Frontier arXiv:2608.25677v1 Announce Type: new Abstract: Parameter-efficient fine-tuning is often assumed to preserve pretrained capabilities because it updates only a small number of parameters. We show that this assumption depends strongly on adapter capacity. We study factual… 23 arXiv — NLP / Computation & Language research 3d ago When RAG Fails to Equalize: Geo-bias in Factual Question Answering over Public Companies arXiv:2608.25717v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) is widely assumed to mitigate factual errors in large language models (LLMs), but it remains unclear whether retrieval uniformly compensates for missing knowledge. We study this question in a… 18 arXiv — NLP / Computation & Language research 3d ago Beam Search, Self-Consistency, and the Limits of Inference-Time Scaling for Grammar-Constrained Text-to-SQL in Small Language Models arXiv:2608.25761v1 Announce Type: new Abstract: One common trade-off in the use of large language models involves reducing the size of the model while increasing the amount of computation at inference time, for example by using a wider beam search. In this paper, we examine the… 23 arXiv — NLP / Computation & Language research 3d ago MoganBert-TR: A Turkish Encoder Foundation Model Trained from Scratch with a CLM-to-MLM Curriculum arXiv:2608.25768v1 Announce Type: new Abstract: Turkish encoder models have adopted modern architectures while leaving the pretraining objective fixed at masked language modelling. This paper introduces MoganBert-TR, a 149M-parameter Turkish encoder foundation model trained from… 16 arXiv — NLP / Computation & Language research 3d ago Localize-Then-Decide Guarantees for LLM Judgments arXiv:2608.25824v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as evaluators to assess output quality and preference alignment, yet providing reliable guarantees of agreement with human judgments remains challenging. Recent work introduces… 21 arXiv — NLP / Computation & Language research 3d ago Unfolding Scientific Papers into Multi-Turn Generation Trajectories for Continued Pre-Training arXiv:2608.25826v1 Announce Type: new Abstract: A recent line of synthetic-data work reconstructs the thinking behind existing text rather than rewriting the text itself, but it operates on short web passages, recovers only local thoughts, and leaves the structure of whole… 12 arXiv — NLP / Computation & Language research 3d ago Skill Issue: Are Skills Language-Invariant in LLMs? arXiv:2608.25832v1 Announce Type: new Abstract: Large language models access knowledge inconsistently across languages, but to what extent do they differ in their skill sets when interacting with different languages? This work quantifies cross-lingual skill inconsistency… 38 arXiv — NLP / Computation & Language research 3d ago Key Point Analysis Needs Structure Recovery: Task Definition, Dataset Diagnosis, and a Structure-Aware Benchmark arXiv:2608.25854v1 Announce Type: new Abstract: Key Point Analysis (KPA) aims to identify a concise set of key points that summarize a collection of arguments together with their prevalence. We argue that KPA is fundamentally a structured prediction problem that requires… 32 arXiv — NLP / Computation & Language research 3d ago Anchoring Bias in LLM-as-a-Judge Systems: Prior Scores Compromise Evaluation Independence arXiv:2608.25869v1 Announce Type: new Abstract: Large language models (LLMs) increasingly assess generated content, giving rise to the LLM-as-a-Judge paradigm. These systems now score outputs, filter content, and gate iterative refinement in production pipelines, where each… 21 Page 7 of 10 · 500 articles ← Newer Older →
