Library

Subject

Tags

113,720 matches · cs.CL

#
001	(Towards) Scalable Reliable Automated Evaluation with Large Language Models	arXiv	Paper	Bertil Braun et al.	Yesterday
002	A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding	arXiv	Paper	Yuesong Liu et al.	Yesterday
003	AI systems and the reproduction of (standard) language ideologies in World Englishes	arXiv	Paper	Kingsley Ugwuanyi	Yesterday
004	AISPA: User-Centric System Prompt Auditing for Large Language Model Applications	arXiv	Paper	Xiangning Lin et al.	Yesterday
005	AWARE-FX: An Auditable Knowledge-Guided AI System for Measuring Corporate Foreign-Exchange Hedging Disclosure	arXiv	Paper	Qi Wang	Yesterday
006	AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis	arXiv	Paper	Bing Yan et al.	Yesterday
007	AutoSupervision: Closing the Feedback Loop in Scientific Workflows with Grounded Revision Verification	arXiv	Paper	Haobo Li et al.	Yesterday
008	Baikal: Structured Search for Deep Research over Data Lakes	arXiv	Paper	Dhruv Agarwal et al.	Yesterday
009	Beyond Borrowed Histories: Person-Aligned User Simulation for Interactive Role-Playing Evaluation	arXiv	Paper	Yuhang Zhu et al.	Yesterday
010	Beyond Feeling Better: Capability-Sustaining Emotional Dialogue as a Longitudinal Research Paradigm	arXiv	Paper	Ming Wang et al.	Yesterday
011	Beyond Sentiment: Structured Information Extraction from Financial News	arXiv	Paper	Daohan Zhu et al.	Yesterday
012	Beyond Similarity: Grounded Agentic Extraction and Expert-Adjudicated Evaluation of Intertextuality in Classical Chinese Histories	arXiv	Paper	Zhaoji Wang et al.	Yesterday
013	Beyond a Single Judge: Simulating Social Persona Panels for Generative UI Evaluation	arXiv	Paper	Zheng Wu et al.	Yesterday
014	CACHE-UK: A Stability-Aware Memory Editor for Sequentially Updated Quantized LLMs in Finance	arXiv	Paper	Anubhav Lakra et al.	Yesterday
015	CDAE: Enhancing Perturbation Robustness in Pretrained Language Models with Contrastive Denoising	arXiv	Paper	Sina Heydari et al.	Yesterday
016	Can Agents Deceive? Evaluating Reasoning and Deception in ParliamentBench using a Social Deduction Game	arXiv	Paper	Niklas Bauer et al.	Yesterday
017	Can LVLMs Uncover the Truth Behind Visual Illusions? An Analysis of Perceptual and Reasoning Capabilities	arXiv	Paper	Liangjie Zhao et al.	Yesterday
018	Can Large Language Models Execute Parent Orders?	arXiv	Paper	Zane Shen et al.	Yesterday
019	Causal Discovery with Inverted Self-attention for Multivariate Time Series	arXiv	Paper	Yusen Liu et al.	Yesterday
020	Challenges in annotations by humans and LLMs: A case study of evaluative language	arXiv	Paper	Mirela Imamovic et al.	Yesterday
021	Change2Task: From Repository Changes to Executable Coding Agent Tasks and Environments	arXiv	Paper	Haomin Qi et al.	Yesterday
022	ChronoMem: Version Control and Semantic Rollback for Large Language Model Agent Memory	arXiv	Paper	Yongye Su et al.	Yesterday
023	Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO	arXiv	Paper	Xilin Jiang et al.	Yesterday
024	Correlation between prosody and pragmatics: A case study of the discourse marker hālā `now' in Persian	arXiv	Paper	Soleiman Ghaderi et al.	Yesterday
025	Creative Transformation in Literary Texts: Modelling Change Across Representational Levels	arXiv	Paper	Ioana-Roxana Boriceanu et al.	Yesterday
026	DualAnchor: Preserving Language Priors and Improving Lexical Fidelity in Gloss-Free Sign Language Translation	arXiv	Paper	Hongbin Zhang et al.	Yesterday
027	EMBL AI Librarian: Life-Sciences Knowledge Layer for AI Agents	arXiv	Paper	Luigi Sigillo et al.	Yesterday
028	Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations	arXiv	Paper	Pere Martra et al.	Yesterday
029	Fidelity Is Not Safety: Gently-Compressed LLMs Pass Every Data-Free Quality Guard Yet Invent Procedure Steps in Agentic Execution	arXiv	Paper	I. Kennedy et al.	Yesterday
030	FinSMART: Financial Sentiment Analysis for Algorithmic Trading through Market-Aligned Reinforcement Learning	arXiv	Paper	Giorgos Iacovides et al.	Yesterday
031	FinanceHarness: Autonomous Financial Deep Research Framework	arXiv	Paper	Yijia Xiao et al.	Yesterday
032	From Single- to Cross-Document: Benchmarking Multi-Granularity Event Analysis of Large Language Models	arXiv	Paper	Tao Wen et al.	Yesterday
033	Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering	arXiv	Paper	Junlin Yang et al.	Yesterday
034	GGC: Selective Query Correction for Reliable Text-to-SPARQL Generation	arXiv	Paper	Ziyi Yang et al.	Yesterday
035	GLM-RAG: Graph Language Models for Graph-Based Retrieval-Augmented Generation	arXiv	Paper	Maya Arseven et al.	Yesterday
036	Generative AI and linguistic diversity in academic writing and publishing: Perspectives from World Englishes	arXiv	Paper	Kingsley Ugwuanyi et al.	Yesterday
037	Gradient-free Task-Conditioned Retrieval for On-Device In-Context Learning	arXiv	Paper	Xinyu Luo et al.	Yesterday
038	Harness-G: A Graph-Structured Harness for Search Agents	arXiv	Paper	Yanning Hou et al.	Yesterday
039	ICLE++: Modeling Fine-Grained Traits for Holistic Essay Scoring	arXiv	Paper	Shengjie Li et al.	Yesterday
040	IFHierBench: Hierarchical Instruction Following for Large Language Models	arXiv	Paper	Yuetian Mao et al.	Yesterday
041	Improving Mental Health Screening and Early Risk Detection in Spanish	arXiv	Paper	Andreu Casamayor-Segarra et al.	Yesterday
042	Inducing language models to assert their own consciousness restores human beliefs and values	arXiv	Paper	Junsol Kim et al.	Yesterday
043	LEEPS: Latent-Guided Explore-Exploit Prompt Sampling for Efficient RLVR in Large Language Models	arXiv	Paper	Shuang Liang et al.	Yesterday
044	LLMs struggle to simulate human belief updates in controlled environments	arXiv	Paper	Sebastian Pohl et al.	Yesterday
045	Lightning OPD 2.0: Mitigating Style Bias in Cross-Teacher On-Policy Distillation for Large Reasoning Models	arXiv	Paper	Yecheng Wu et al.	Yesterday
046	Looped Transformers with Source-Centered State Evolution	arXiv	Paper	Bum Jun Kim et al.	Yesterday
047	MORFES: A Benchmark for Productive Inflectional Competence in Modern Greek	arXiv	Paper	Ioakeim Perros et al.	Yesterday
048	Measuring Alignment With Reader Highlights Net of Position and Length	arXiv	Paper	Kazuki Nakayashiki et al.	Yesterday
049	MemTxn: A Transaction Boundary for Source-Supported Updates and Complete-State Recovery in Agent Memory	arXiv	Paper	Hanshuai Cui et al.	Yesterday
050	Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory	arXiv	Paper	Rubin Wei et al.	Yesterday
051	Metaphor Tracer: A Theory-Informed Analysis of Hidden States	arXiv	Paper	Marc Heimann et al.	Yesterday
052	ORCA-bench: How Ready Are Language Model Agents for Oncall?	arXiv	Paper	Albert Gong et al.	Yesterday
053	OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models	arXiv	Paper	Qiushi Sun et al.	Yesterday
054	PCAP-LM: An LLM-Native Text Representation for TLS Bulk Traffic Analysis	arXiv	Paper	Xavier Marjou et al.	Yesterday
055	Prox: Training-Free FFN Activation Sparsity via Approximate Intermediate-Channel Salience in LLMs	arXiv	Paper	Jinyi Liu et al.	Yesterday
056	RRM: Experience-Driven Reflective Retrieval Memory for Long-Horizon Multimodal Reasoning	arXiv	Paper	Jingxiang Fan et al.	Yesterday
057	ReDiPPO: Reference-Guided Value Calibration and Discrepancy-Aware Token Reweighting for Mathematical Reasoning	arXiv	Paper	Zhenrong Zhang et al.	Yesterday
058	Reasoning Consensus: Structural Ensembling of LLM Reasoning via Weighted DAG Aggregation	arXiv	Paper	Amruta Parulekar et al.	Yesterday
059	Recall Before You Rank: Similarity-Guided Top-$K$ Reuse for Efficient Long-Context Attention	arXiv	Paper	Wenshuai Yao et al.	Yesterday
060	RepBench: Compiling Benchmarks into Capability Representations for Large Language Models	arXiv	Paper	Yanshi Li et al.	Yesterday

Showing 60 of 113,720 documents · scroll for more