{"total":92,"rows":[{"id":"2310.07521","title":"Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity","created":"2023-10-11","cited_by_count":206,"area":null},{"id":"2305.13281","title":"LM vs LM: Detecting Factual Errors via Cross Examination","created":"2023-05-22","cited_by_count":156,"area":null},{"id":"2212.07981","title":"Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation","created":"2022-12-15","cited_by_count":142,"area":null},{"id":"2307.06908","title":"Generating Benchmarks for Factuality Evaluation of Language Models","created":"2023-07-13","cited_by_count":105,"area":null},{"id":"2403.02901","title":"A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methods","created":"2024-03-05","cited_by_count":102,"area":null},{"id":"2311.01740","title":"SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistency","created":"2023-11-03","cited_by_count":90,"area":null},{"id":"2309.06794","title":"Cognitive Mirage: A Review of Hallucinations in Large Language Models","created":"2023-09-13","cited_by_count":84,"area":null},{"id":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66,"area":null},{"id":"2402.08785","title":"InstructGraph: Boosting Large Language Models via Graph-centric Instruction Tuning and Preference Alignment","created":"2024-02-13","cited_by_count":56,"area":"lr"},{"id":"2406.11289","title":"A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Models","created":"2024-06-17","cited_by_count":52,"area":null},{"id":"2506.18959","title":"From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents","created":"2025-06-23","cited_by_count":51,"area":"lr"},{"id":"2306.09983","title":"Evaluating Superhuman Models with Consistency Checks","created":"2023-06-16","cited_by_count":47,"area":null},{"id":"2402.10294","title":"LAVE: LLM-Powered Agent Assistance and Language Augmentation for Video Editing","created":"2024-02-15","cited_by_count":47,"area":"agents"},{"id":"2405.00467","title":"Harnessing the Power of Multiple Minds: Lessons Learned from LLM Routing","created":"2024-05-01","cited_by_count":46,"area":null},{"id":"2310.18344","title":"Chainpoll: A high efficacy method for LLM hallucination detection","created":"2023-10-22","cited_by_count":39,"area":null},{"id":"2303.06273","title":"Consistency Analysis of ChatGPT","created":"2023-03-11","cited_by_count":37,"area":null},{"id":"2403.12503","title":"Securing Large Language Models: Threats, Vulnerabilities and Responsible Practices","created":"2024-03-19","cited_by_count":37,"area":null},{"id":"2308.11764","title":"Halo: Estimation and Reduction of Hallucinations in Open-Source Weak Large Language Models","created":"2023-08-22","cited_by_count":36,"area":null},{"id":"2305.14956","title":"Editing Common Sense in Transformers","created":"2023-05-24","cited_by_count":28,"area":null},{"id":"2401.01989","title":"Revisiting Zero-Shot Abstractive Summarization in the Era of Large Language Models from the Perspective of Position Bias","created":"2024-01-03","cited_by_count":28,"area":null},{"id":"2503.17662","title":"Enhancing Persona Consistency for LLMs' Role-Playing using Persona-Aware Contrastive Learning","created":"2025-03-22","cited_by_count":27,"area":null},{"id":"2412.06676","title":"I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token","created":"2024-12-09","cited_by_count":26,"area":null},{"id":"2309.13356","title":"Probing the Moral Development of Large Language Models through Defining Issues Test","created":"2023-09-23","cited_by_count":25,"area":"lr"},{"id":"2406.06950","title":"A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation","created":"2024-06-11","cited_by_count":21,"area":null},{"id":"2410.18889","title":"Are LLMs Better than Reported? Detecting Label Errors and Mitigating Their Effect on Model Performance","created":"2024-10-24","cited_by_count":20,"area":null},{"id":"2502.04134","title":"The Order Effect: Investigating Prompt Sensitivity to Input Order in LLMs","created":"2025-02-06","cited_by_count":19,"area":null},{"id":"2311.07884","title":"Fair Abstractive Summarization of Diverse Perspectives","created":"2023-11-14","cited_by_count":17,"area":null},{"id":"2308.09138","title":"Semantic Consistency for Assuring Reliability of Large Language Models","created":"2023-08-17","cited_by_count":15,"area":null},{"id":"2404.01667","title":"METAL: Towards Multilingual Meta-Evaluation","created":"2024-04-02","cited_by_count":15,"area":null},{"id":"2404.11184","title":"FIZZ: Factual Inconsistency Detection by Zoom-in Summary and Zoom-out Document","created":"2024-04-17","cited_by_count":15,"area":null},{"id":"2304.00472","title":"Querying Large Language Models with SQL","created":"2023-04-02","cited_by_count":14,"area":null},{"id":"2505.00268","title":"Consistency in Language Models: Current Landscape, Challenges, and Future Directions","created":"2025-05-01","cited_by_count":14,"area":null},{"id":"2306.06199","title":"Reliability Check: An Analysis of GPT-3's Response to Sensitive Topics and Prompt Wording","created":"2023-06-09","cited_by_count":13,"area":null},{"id":"2402.09334","title":"AuditLLM: A Tool for Auditing Large Language Models Using Multiprobe Approach","created":"2024-02-14","cited_by_count":11,"area":null},{"id":"2406.03993","title":"Assessing LLMs for Zero-shot Abstractive Summarization Through the Lens of Relevance Paraphrasing","created":"2024-06-06","cited_by_count":11,"area":null},{"id":"2401.16713","title":"Prospects for inconsistency detection using large language models and sheaves","created":"2024-01-30","cited_by_count":10,"area":null},{"id":"2411.02454","title":"Graph-based Confidence Calibration for Large Language Models","created":"2024-11-03","cited_by_count":10,"area":null},{"id":"2403.05266","title":"ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Models","created":"2024-03-08","cited_by_count":9,"area":null},{"id":"2405.20588","title":"DAFNet: Dynamic Auxiliary Fusion for Sequential Model Editing in Large Language Models","created":"2024-05-31","cited_by_count":9,"area":null},{"id":"2402.09346","title":"LLMAuditor: A Framework for Auditing Large Language Models Using Human-in-the-Loop","created":"2024-02-14","cited_by_count":8,"area":null},{"id":"2408.08545","title":"SelectLLM: Query-Aware Efficient Selection Algorithm for Large Language Models","created":"2024-08-16","cited_by_count":8,"area":null},{"id":"2408.11869","title":"ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA","created":"2024-08-19","cited_by_count":8,"area":null},{"id":"2505.21701","title":"Do We Know What LLMs Don't Know? A Study of Consistency in Knowledge Probing","created":"2025-05-27","cited_by_count":8,"area":null},{"id":"2508.20890","title":"PromptSleuth: Detecting Prompt Injection via Semantic Intent Invariance","created":"2025-08-28","cited_by_count":8,"area":"safety"},{"id":"2305.12544","title":"Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models","created":"2023-05-21","cited_by_count":7,"area":null},{"id":"2410.17218","title":"Creativity in AI: Progresses and Challenges","created":"2024-10-22","cited_by_count":7,"area":null},{"id":"2311.08117","title":"Insights into Classifying and Mitigating LLMs' Hallucinations","created":"2023-11-14","cited_by_count":6,"area":null},{"id":"2311.09668","title":"Improving the Generation Quality of Watermarked Large Language Models via Word Importance Scoring","created":"2023-11-16","cited_by_count":6,"area":"safety"},{"id":"2411.03883","title":"MEG: Medical Knowledge-Augmented Large Language Models for Question Answering","created":"2024-11-06","cited_by_count":6,"area":null},{"id":"2505.05070","title":"Performance Evaluation of Large Language Models in Bangla Consumer Health Query Summarization","created":"2025-05-08","cited_by_count":6,"area":null},{"id":"2311.06697","title":"Trusted Source Alignment in Large Language Models","created":"2023-11-12","cited_by_count":4,"area":null},{"id":"2311.09741","title":"P^3SUM: Preserving Author's Perspective in News Summarization with Diffusion Language Models","created":"2023-11-16","cited_by_count":4,"area":"diffusion"},{"id":"2402.14359","title":"Rethinking Scientific Summarization Evaluation: Grounding Explainable Metrics on Facet-aware Benchmark","created":"2024-02-22","cited_by_count":4,"area":"lr"},{"id":"2405.08890","title":"Language-Guided Self-Supervised Video Summarization Using Text Semantic Matching Considering the Diversity of the Video","created":"2024-05-14","cited_by_count":3,"area":null},{"id":"2407.00453","title":"PerSEval: Assessing Personalization in Text Summarizers","created":"2024-06-29","cited_by_count":3,"area":null},{"id":"2505.20487","title":"InFact: Informativeness Alignment for Improved LLM Factuality","created":"2025-05-26","cited_by_count":3,"area":null},{"id":"2506.00773","title":"Dynamic Chunking and Selection for Reading Comprehension of Ultra-Long Context in Large Language Models","created":"2025-06-01","cited_by_count":3,"area":null},{"id":"2604.17284","title":"HalluClear: Diagnosing, Evaluating and Mitigating Hallucinations in GUI Agents","created":"2026-04-19","cited_by_count":3,"area":"agents"},{"id":"2307.07544","title":"A Dialogue System for Assessing Activities of Daily Living: Improving Consistency with Grounded Knowledge","created":"2023-07-15","cited_by_count":2,"area":null},{"id":"2403.03750","title":"German also Hallucinates! Inconsistency Detection in News Summaries with the Absinth Dataset","created":"2024-03-06","cited_by_count":2,"area":null},{"id":"2406.15809","title":"LaMSUM: Amplifying Voices Against Harassment through LLM Guided Extractive Summarization of User Incident Reports","created":"2024-06-22","cited_by_count":2,"area":null},{"id":"2406.19497","title":"Inclusivity in Large Language Models: Personality Traits and Gender Bias in Scientific Abstracts","created":"2024-06-27","cited_by_count":2,"area":null},{"id":"2409.19507","title":"A Critical Look at Meta-evaluating Summarisation Evaluation Metrics","created":"2024-09-29","cited_by_count":2,"area":null},{"id":"2412.02819","title":"CNNSum: Exploring Long-Context Summarization with Large Language Models in Chinese Novels","created":"2024-12-03","cited_by_count":2,"area":null},{"id":"2412.12040","title":"How Private are Language Models in Abstractive Summarization?","created":"2024-12-16","cited_by_count":2,"area":null},{"id":"2502.20647","title":"Consistency Evaluation of News Article Summaries Generated by Large (and Small) Language Models","created":"2025-02-28","cited_by_count":2,"area":null},{"id":"2510.04392","title":"Improving Consistency in Retrieval-Augmented Systems with Group Similarity Rewards","created":"2025-10-05","cited_by_count":2,"area":"rag"},{"id":"2602.16843","title":"BanglaSummEval: Reference-Free Factual Consistency Evaluation for Bangla Summarization","created":"2026-02-18","cited_by_count":2,"area":null},{"id":"2309.12075","title":"Prompt Tuned Embedding Classification for Multi-Label Industry Sector Allocation","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2310.13610","title":"Make Your Decision Convincing! A Unified Two-Stage Framework: Self-Attribution and Decision-Making","created":"2023-10-20","cited_by_count":1,"area":null},{"id":"2312.06901","title":"Unsupervised Extractive Summarization with Learnable Length Control Strategies","created":"2023-12-12","cited_by_count":1,"area":null},{"id":"2407.17150","title":"SimCT: A Simple Consistency Test Protocol in LLMs Development Lifecycle","created":"2024-07-24","cited_by_count":1,"area":null},{"id":"2409.17588","title":"DualCoTs: Dual Chain-of-Thoughts Prompting for Sentiment Lexicon Expansion of Idioms","created":"2024-09-26","cited_by_count":1,"area":"lr"},{"id":"2502.10200","title":"Dynamic Reinforcement Learning for Actors","created":"2025-02-14","cited_by_count":1,"area":"deeprl"},{"id":"2502.19209","title":"Bi'an: A Bilingual Benchmark and Model for Hallucination Detection in Retrieval-Augmented Generation","created":"2025-02-26","cited_by_count":1,"area":"rag"},{"id":"2503.11346","title":"AIstorian lets AI be a historian: A KG-powered multi-agent system for accurate biography generation","created":"2025-03-14","cited_by_count":1,"area":"agents"},{"id":"2505.21218","title":"Pretrained LLMs Learn Multiple Types of Uncertainty","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2506.17864","title":"QueueEDIT: Structural Self-Correction for Sequential Model Editing in LLMs","created":"2025-06-22","cited_by_count":1,"area":null},{"id":"2510.15513","title":"Temporal Referential Consistency: Do LLMs Favor Sequences Over Absolute Time References?","created":"2025-10-17","cited_by_count":1,"area":null},{"id":"2603.13259","title":"How Transformers Reject Wrong Answers: Rotational Dynamics of Factual Constraint Processing","created":"2026-02-25","cited_by_count":1,"area":"mechinterp"},{"id":"2408.04114","title":"Zero-shot Factual Consistency Evaluation Across Domains","created":"2024-08-07","cited_by_count":0,"area":null},{"id":"2506.18036","title":"Markov-Enhanced Clustering for Long Document Summarization: Tackling the 'Lost in the Middle' Challenge with Large Language Models","created":"2025-06-22","cited_by_count":0,"area":null},{"id":"2509.00325","title":"GIER: Gap-Driven Self-Refinement for Large Language Models","created":"2025-08-30","cited_by_count":0,"area":null},{"id":"2509.05741","title":"Enhancing Factual Accuracy and Citation Generation in LLMs via Multi-Stage Self-Verification","created":"2025-09-06","cited_by_count":0,"area":"lr"},{"id":"2602.22070","title":"Language Models Exhibit Inconsistent Biases Towards Algorithmic Agents and Human Experts","created":"2026-02-25","cited_by_count":0,"area":"agents"},{"id":"2604.10557","title":"LLMs Should Incorporate Explicit Mechanisms for Human Empathy","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2606.08000","title":"Summarization is Not Dead Yet","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2606.13171","title":"NTS-CoT: Mitigating Hallucinations in LLM-based News Timeline Summarization with Chain-of-Thought Reasoning","created":"2026-06-11","cited_by_count":0,"area":"lr"},{"id":"2607.21010","title":"Reexamining zero-shot summarization: Empirical investigation of trustworthiness of LLM-summarizers","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2608.03655","title":"Decoupling Generation and Selection for Budget-Constrained Faithful Summarization","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.07250","title":"Artificial Intelligence Can Match Domain Experts in Evidence Extraction and Critical Appraisal of Microbial Oncogenesis Research Publications","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2610.18497","title":"Judges Follow the Reference: The Derivation Gap in Verifying Tool-Call Arguments","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}