{"total":111,"rows":[{"id":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186,"area":null},{"id":"2307.16877","title":"Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering","created":"2023-07-31","cited_by_count":151,"area":null},{"id":"2307.11019","title":"Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation","created":"2023-07-20","cited_by_count":147,"area":null},{"id":"2401.08406","title":"RAG vs Fine-tuning: Pipelines, Tradeoffs, and a Case Study on Agriculture","created":"2024-01-16","cited_by_count":81,"area":"rag"},{"id":"2407.08223","title":"Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting","created":"2024-07-11","cited_by_count":77,"area":"rag"},{"id":"2407.09413","title":"SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers","created":"2024-07-12","cited_by_count":75,"area":null},{"id":"2404.13081","title":"SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs","created":"2024-04-17","cited_by_count":67,"area":null},{"id":"2312.03052","title":"Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models","created":"2023-12-05","cited_by_count":66,"area":"lr"},{"id":"2401.02038","title":"Understanding LLMs: A Comprehensive Overview from Training to Inference","created":"2024-01-04","cited_by_count":59,"area":null},{"id":"2503.12491","title":"CAKE: Cascading and Adaptive KV Cache Eviction with Layer Preferences","created":"2025-03-16","cited_by_count":58,"area":"inference"},{"id":"2312.16171","title":"Principled Instructions Are All You Need for Questioning LLaMA-1/2, GPT-3.5/4","created":"2023-12-26","cited_by_count":48,"area":null},{"id":"2501.02189","title":"A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges","created":"2025-01-04","cited_by_count":47,"area":"mllm"},{"id":"2503.01013","title":"TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop","created":"2025-03-02","cited_by_count":39,"area":null},{"id":"2502.06065","title":"Benchmarking Prompt Sensitivity in Large Language Models","created":"2025-02-09","cited_by_count":38,"area":null},{"id":"2310.02567","title":"Improving Automatic VQA Evaluation Using Large Language Models","created":"2023-10-04","cited_by_count":37,"area":null},{"id":"2306.14899","title":"FunQA: Towards Surprising Video Comprehension","created":"2023-06-26","cited_by_count":35,"area":null},{"id":"2407.05355","title":"VideoCoT: A Video Chain-of-Thought Dataset with Active Annotation Tool","created":"2024-07-07","cited_by_count":35,"area":"lr"},{"id":"2412.18148","title":"Are We in the AI-Generated Text World Already? Quantifying and Monitoring AIGT on Social Media","created":"2024-12-24","cited_by_count":35,"area":null},{"id":"2310.07343","title":"How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances","created":"2023-10-11","cited_by_count":33,"area":null},{"id":"2502.05234","title":"Optimizing Temperature for Language Models with Multi-Sample Inference","created":"2025-02-07","cited_by_count":33,"area":"lr"},{"id":"2406.18678","title":"Few-shot Personalization of LLMs with Mis-aligned Responses","created":"2024-06-26","cited_by_count":32,"area":null},{"id":"2505.06311","title":"Defending against Indirect Prompt Injection by Instruction Detection","created":"2025-05-08","cited_by_count":32,"area":"rag"},{"id":"2406.13035","title":"D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models","created":"2024-06-18","cited_by_count":31,"area":"inference"},{"id":"2503.13517","title":"CURIE: Evaluating LLMs On Multitask Scientific Long Context Understanding and Reasoning","created":"2025-03-14","cited_by_count":28,"area":"lr"},{"id":"2406.04291","title":"Stratified Prediction-Powered Inference for Hybrid Language Model Evaluation","created":"2024-06-06","cited_by_count":26,"area":null},{"id":"2404.09696","title":"Are Large Language Models Reliable Argument Quality Annotators?","created":"2024-04-15","cited_by_count":24,"area":null},{"id":"2410.22932","title":"Multi-Agent Large Language Models for Conversational Task-Solving","created":"2024-10-30","cited_by_count":24,"area":"agents"},{"id":"2503.02846","title":"Mask-DPO: Generalizable Fine-grained Factuality Alignment of LLMs","created":"2025-03-04","cited_by_count":24,"area":"alignment"},{"id":"2502.00409","title":"Doing More with Less: A Survey on Routing Strategies for Resource Optimisation in Large Language Model-Based Systems","created":"2025-02-01","cited_by_count":20,"area":null},{"id":"2406.05317","title":"LoCoCo: Dropping In Convolutions for Long Context Compression","created":"2024-06-08","cited_by_count":19,"area":"inference"},{"id":"2412.04782","title":"A Survey of Sustainability in Large Language Models: Applications, Economics, and Challenges","created":"2024-12-06","cited_by_count":18,"area":null},{"id":"2412.18295","title":"Pirates of the RAG: Adaptively Attacking LLMs to Leak Knowledge Bases","created":"2024-12-24","cited_by_count":18,"area":"rag"},{"id":"2501.19378","title":"TableMaster: A Recipe to Advance Table Understanding with Language Models","created":"2025-01-31","cited_by_count":18,"area":null},{"id":"2502.16636","title":"Visual-RAG: Benchmarking Text-to-Image Retrieval Augmented Generation for Visual Knowledge Intensive Queries","created":"2025-02-23","cited_by_count":16,"area":"rag"},{"id":"2406.13282","title":"Understanding the RoPE Extensions of Long-Context LLMs: An Attention Perspective","created":"2024-06-19","cited_by_count":15,"area":null},{"id":"2407.05138","title":"Are LLMs Correctly Integrated into Software Systems?","created":"2024-07-06","cited_by_count":15,"area":"rag"},{"id":"2412.16100","title":"Logical Consistency of Large Language Models in Fact-checking","created":"2024-12-20","cited_by_count":15,"area":null},{"id":"2407.04693","title":"ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models","created":"2024-07-05","cited_by_count":14,"area":null},{"id":"2601.04888","title":"SmartSearch: Process Reward-Guided Query Refinement for Search Agents","created":"2026-01-08","cited_by_count":14,"area":"agents"},{"id":"2602.12268","title":"CM2: Reinforcement Learning with Checklist Rewards for Multi-Turn and Multi-Step Agentic Tool Use","created":"2026-02-12","cited_by_count":14,"area":"agents"},{"id":"2311.09841","title":"Leveraging LLMs in Scholarly Knowledge Graph Question Answering","created":"2023-11-16","cited_by_count":13,"area":null},{"id":"2411.14401","title":"Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding","created":"2024-11-21","cited_by_count":13,"area":"mllm"},{"id":"2409.08202","title":"What Makes a Maze Look Like a Maze?","created":"2024-09-12","cited_by_count":11,"area":"mllm"},{"id":"2409.09269","title":"Guiding Vision-Language Model Selection for Visual Question-Answering Across Tasks, Domains, and Knowledge Types","created":"2024-09-14","cited_by_count":10,"area":"mllm"},{"id":"2510.07651","title":"OBCache: Optimal Brain KV Cache Pruning for Efficient Long-Context LLM Inference","created":"2025-10-09","cited_by_count":10,"area":"inference"},{"id":"2501.00269","title":"A review of faithfulness metrics for hallucination assessment in Large Language Models","created":"2024-12-31","cited_by_count":9,"area":null},{"id":"2405.06034","title":"Bayesian Prediction-Powered Inference","created":"2024-05-09","cited_by_count":8,"area":null},{"id":"2410.15107","title":"Toward Robust RALMs: Revealing the Impact of Imperfect Retrieval on Retrieval-Augmented Language Models","created":"2024-10-19","cited_by_count":8,"area":"rag"},{"id":"2412.07420","title":"RAG-based Question Answering over Heterogeneous Data and Text","created":"2024-12-10","cited_by_count":7,"area":null},{"id":"2405.12669","title":"A Survey on Multi-modal Machine Translation: Tasks, Methods and Challenges","created":"2024-05-21","cited_by_count":6,"area":null},{"id":"2505.15323","title":"Improving LLM First-Token Predictions in Multiple-Choice Question Answering via Output Prefilling","created":"2025-05-21","cited_by_count":6,"area":null},{"id":"2402.07812","title":"Retrieval Augmented Thought Process for Private Data Handling in Healthcare","created":"2024-02-12","cited_by_count":5,"area":"lr"},{"id":"2402.08472","title":"Large Language Models for the Automated Analysis of Optimization Algorithms","created":"2024-02-13","cited_by_count":5,"area":null},{"id":"2403.14443","title":"Language Models Can Reduce Asymmetry in Information Markets","created":"2024-03-21","cited_by_count":5,"area":null},{"id":"2502.16358","title":"Wrong Answers Can Also Be Useful: PlausibleQA -- A Large-Scale QA Dataset with Answer Plausibility Scores","created":"2025-02-22","cited_by_count":5,"area":null},{"id":"2508.20766","title":"Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection","created":"2025-08-28","cited_by_count":5,"area":"alignment"},{"id":"2509.08604","title":"Memorization in Large Language Models in Medicine: Prevalence, Characteristics, and Implications","created":"2025-09-10","cited_by_count":5,"area":null},{"id":"2310.09725","title":"KGQuiz: Evaluating the Generalization of Encoded Knowledge in Large Language Models","created":"2023-10-15","cited_by_count":4,"area":null},{"id":"2401.02132","title":"DCR-Consistency: Divide-Conquer-Reasoning for Consistency Evaluation and Improvement of Large Language Models","created":"2024-01-04","cited_by_count":4,"area":"lr"},{"id":"2406.17158","title":"DEXTER: A Benchmark for open-domain Complex Question Answering using LLMs","created":"2024-06-24","cited_by_count":4,"area":null},{"id":"2407.12529","title":"Crafting the Path: Robust Query Rewriting for Information Retrieval","created":"2024-07-17","cited_by_count":4,"area":null},{"id":"2408.09946","title":"Fine-Grained and Thematic Evaluation of LLMs in Social Deduction Game","created":"2024-08-19","cited_by_count":4,"area":null},{"id":"2503.01330","title":"WeightedKV: Attention Scores Weighted Key-Value Cache Merging for Large Language Models","created":"2025-03-03","cited_by_count":4,"area":"inference"},{"id":"2504.07109","title":"OSCAR: Online Soft Compression And Reranking","created":"2025-03-17","cited_by_count":4,"area":"rag"},{"id":"2505.17694","title":"CoDec: Prefix-Shared Decoding Kernel for LLMs","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2507.08443","title":"KGRAG-Ex: Explainable Retrieval-Augmented Generation with Knowledge Graph-based Perturbations","created":"2025-07-11","cited_by_count":4,"area":"rag"},{"id":"2508.06056","title":"RAGTrace: Understanding and Refining Retrieval-Generation Dynamics in Retrieval-Augmented Generation","created":"2025-08-08","cited_by_count":4,"area":"rag"},{"id":"2601.02536","title":"MovieRecapsQA: A Multimodal Open-Ended Video Question-Answering Benchmark","created":"2026-01-05","cited_by_count":4,"area":null},{"id":"2504.03651","title":"Echo: Efficient Co-Scheduling of Hybrid Online-Offline Tasks for Large Language Model Serving","created":"2025-03-01","cited_by_count":3,"area":"inference"},{"id":"2506.07458","title":"KScope: A Framework for Characterizing the Knowledge Status of Language Models","created":"2025-06-09","cited_by_count":3,"area":null},{"id":"2506.13171","title":"Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches","created":"2025-06-16","cited_by_count":3,"area":"agents"},{"id":"2509.09715","title":"Investigating Symbolic Triggers of Hallucination in Gemma Models Across HaluEval and TruthfulQA","created":"2025-09-09","cited_by_count":3,"area":null},{"id":"2510.02827","title":"StepChain GraphRAG: Reasoning Over Knowledge Graphs for Multi-Hop Question Answering","created":"2025-10-03","cited_by_count":3,"area":"lr"},{"id":"2512.08936","title":"A Principle-based Framework for the Development and Evaluation of Large Language Models for Health and Wellness","created":"2025-10-23","cited_by_count":3,"area":null},{"id":"2607.05861","title":"Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization","created":"2026-07-07","cited_by_count":3,"area":"lr"},{"id":"2410.17655","title":"Mapping the Media Landscape: Predicting Factual Reporting and Political Bias Through Web Interactions","created":"2024-10-23","cited_by_count":2,"area":null},{"id":"2503.16581","title":"Investigating Retrieval-Augmented Generation in Quranic Studies: A Study of 13 Open-Source Large Language Models","created":"2025-03-20","cited_by_count":2,"area":"rag"},{"id":"2505.08905","title":"Grounding Synthetic Data Evaluations of Language Models in Unsupervised Document Corpora","created":"2025-05-13","cited_by_count":2,"area":"synth"},{"id":"2506.08364","title":"Structure-Augmented Reasoning Generation","created":"2025-06-10","cited_by_count":2,"area":"lr"},{"id":"2510.13103","title":"ESI: Epistemic Uncertainty Quantification via Semantic-preserving Intervention for Large Language Models","created":"2025-10-15","cited_by_count":2,"area":null},{"id":"2605.15393","title":"LPDS: Evaluating LLM Robustness Through Logic-Preserving Difficulty Scaling","created":"2026-05-14","cited_by_count":2,"area":null},{"id":"2406.13232","title":"Towards Robust Evaluation: A Comprehensive Taxonomy of Datasets and Metrics for Open Domain Question Answering in the Era of Large Language Models","created":"2024-06-19","cited_by_count":1,"area":null},{"id":"2505.03361","title":"Interpretable Zero-shot Learning with Infinite Class Concepts","created":"2025-05-06","cited_by_count":1,"area":null},{"id":"2505.03745","title":"AccLLM: Accelerating Long-Context LLM Inference Via Algorithm-Hardware Co-Design","created":"2025-04-07","cited_by_count":1,"area":null},{"id":"2506.23743","title":"Positional Bias in Binary Question Answering: How Uncertainty Shapes Model Preferences","created":"2025-06-30","cited_by_count":1,"area":null},{"id":"2507.00509","title":"TeamCMU at Touch\\'e: Adversarial Co-Evolution for Advertisement Integration and Detection in Conversational Search","created":"2025-07-01","cited_by_count":1,"area":"rag"},{"id":"2507.05638","title":"LLMs are Introvert","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2509.10843","title":"Evaluating Large Language Models for Evidence-Based Clinical Question Answering","created":"2025-09-13","cited_by_count":1,"area":"rag"},{"id":"2602.21059","title":"An Expert Schema for Evaluating Large Language Model Errors in Scholarly Question-Answering Systems","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2604.26197","title":"Hierarchical Long-Term Semantic Memory for LinkedIn's Hiring Agent","created":"2026-04-29","cited_by_count":1,"area":"agents"},{"id":"2605.07234","title":"Reformulating KV Cache Eviction Problem for Long-Context LLM Inference","created":"2026-05-08","cited_by_count":1,"area":"inference"},{"id":"2401.07237","title":"Distilling Event Sequence Knowledge From Large Language Models","created":"2024-01-14","cited_by_count":0,"area":null},{"id":"2406.15173","title":"\\'Evaluation des capacit\\'es de r\\'eponse de larges mod\\`eles de langage (LLM) pour des questions d'historiens","created":"2024-06-21","cited_by_count":0,"area":null},{"id":"2411.00056","title":"Generating Diverse Negations from Affirmative Sentences","created":"2024-10-30","cited_by_count":0,"area":null},{"id":"2411.10813","title":"Information Anxiety in Large Language Models","created":"2024-11-16","cited_by_count":0,"area":null},{"id":"2502.16540","title":"D2S-FLOW: Automated Parameter Extraction from Datasheets for SPICE Model Generation Using Large Language Models","created":"2025-02-23","cited_by_count":0,"area":null},{"id":"2505.16293","title":"Augmenting LLM Reasoning with Dynamic Notes Writing for Complex QA","created":"2025-05-22","cited_by_count":0,"area":"lr"},{"id":"2505.24292","title":"Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play Modules","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2507.09155","title":"OPENXRD: A Comprehensive Benchmark Framework for LLM/MLLM XRD Question Answering","created":"2025-07-12","cited_by_count":0,"area":"mllm"},{"id":"2507.12143","title":"Overview of the Sensemaking Task at the ELOQUENT 2025 Lab: LLMs as Teachers, Students and Evaluators","created":"2025-07-16","cited_by_count":0,"area":null}],"next_cursor":"100"}