{"total":378,"rows":[{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975,"area":null},{"id":"2303.16634","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","created":"2023-03-29","cited_by_count":2276,"area":null},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075,"area":null},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601,"area":null},{"id":"2305.14251","title":"FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation","created":"2023-05-23","cited_by_count":1282,"area":null},{"id":"2305.11738","title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","created":"2023-05-19","cited_by_count":783,"area":"lr"},{"id":"2106.11520","title":"BARTScore: Evaluating Generated Text as Text Generation","created":"2021-06-22","cited_by_count":722,"area":null},{"id":"2305.14627","title":"Enabling Large Language Models to Generate Text with Citations","created":"2023-05-24","cited_by_count":595,"area":null},{"id":"2303.11897","title":"TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering","created":"2023-03-21","cited_by_count":428,"area":null},{"id":"2302.04166","title":"GPTScore: Evaluate as You Desire","created":"2023-02-08","cited_by_count":361,"area":null},{"id":"2106.13822","title":"XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages","created":"2021-06-25","cited_by_count":347,"area":null},{"id":"2104.02112","title":"Efficient Attentions for Long Document Summarization","created":"2021-04-05","cited_by_count":345,"area":null},{"id":"2109.10862","title":"Recursively Summarizing Books with Human Feedback","created":"2021-09-22","cited_by_count":290,"area":null},{"id":"2305.16739","title":"AlignScore: Evaluating Factual Consistency with a Unified Alignment Function","created":"2023-05-26","cited_by_count":288,"area":null},{"id":"2104.13346","title":"Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics","created":"2021-04-27","cited_by_count":287,"area":null},{"id":"2210.08726","title":"RARR: Researching and Revising What Language Models Say, Using Language Models","created":"2022-10-17","cited_by_count":287,"area":null},{"id":"2401.00396","title":"RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models","created":"2023-12-31","cited_by_count":283,"area":"rag"},{"id":"2210.07197","title":"Towards a Unified Multi-Dimensional Evaluator for Text Generation","created":"2022-10-13","cited_by_count":264,"area":null},{"id":"2406.15927","title":"Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs","created":"2024-06-22","cited_by_count":259,"area":null},{"id":"2404.10774","title":"MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents","created":"2024-04-16","cited_by_count":257,"area":"rag"},{"id":"2112.12870","title":"Measuring Attribution in Natural Language Generation Models","created":"2021-12-23","cited_by_count":256,"area":null},{"id":"2307.13528","title":"FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios","created":"2023-07-25","cited_by_count":251,"area":null},{"id":"2103.12693","title":"QuestEval: Summarization Asks for Fact-based Evaluation","created":"2021-03-23","cited_by_count":244,"area":null},{"id":"2406.18403","title":"LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks","created":"2024-06-26","cited_by_count":243,"area":null},{"id":"2406.01297","title":"When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs","created":"2024-06-03","cited_by_count":240,"area":null},{"id":"2102.01672","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","created":"2021-02-02","cited_by_count":239,"area":null},{"id":"2112.08542","title":"QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization","created":"2021-12-16","cited_by_count":236,"area":null},{"id":"2204.06092","title":"ASQA: Factoid Questions Meet Long-Form Answers","created":"2022-04-12","cited_by_count":234,"area":null},{"id":"2112.08608","title":"QuALITY: Question Answering with Long Input Texts, Yes!","created":"2021-12-16","cited_by_count":208,"area":null},{"id":"2310.09219","title":"\"Kelly is a Warm Person, Joseph is a Role Model\": Gender Biases in LLM-Generated Reference Letters","created":"2023-10-13","cited_by_count":199,"area":null},{"id":"2310.06201","title":"Compressing Context to Enhance Inference Efficiency of Large Language Models","created":"2023-10-09","cited_by_count":189,"area":null},{"id":"2103.06332","title":"Hurdles to Progress in Long-form Question Answering","created":"2021-03-10","cited_by_count":167,"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":"2202.06935","title":"Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text","created":"2022-02-14","cited_by_count":155,"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":"2104.08704","title":"A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation","created":"2021-04-18","cited_by_count":138,"area":null},{"id":"2104.08202","title":"$Q^{2}$: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering","created":"2021-04-16","cited_by_count":132,"area":null},{"id":"2104.04302","title":"Annotating and Modeling Fine-grained Factuality in Summarization","created":"2021-04-09","cited_by_count":131,"area":null},{"id":"2109.09784","title":"Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization","created":"2021-08-30","cited_by_count":129,"area":null},{"id":"2304.02554","title":"Human-like Summarization Evaluation with ChatGPT","created":"2023-04-05","cited_by_count":126,"area":null},{"id":"2402.14016","title":"Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment","created":"2024-02-21","cited_by_count":126,"area":null},{"id":"2109.09209","title":"CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization","created":"2021-09-19","cited_by_count":120,"area":null},{"id":"2303.01432","title":"WiCE: Real-World Entailment for Claims in Wikipedia","created":"2023-03-02","cited_by_count":120,"area":null},{"id":"2307.02762","title":"PRD: Peer Rank and Discussion Improve Large Language Model based Evaluations","created":"2023-07-06","cited_by_count":114,"area":null},{"id":"2204.10757","title":"FaithDial: A Faithful Benchmark for Information-Seeking Dialogue","created":"2022-04-22","cited_by_count":109,"area":null},{"id":"2305.10400","title":"What You See is What You Read? Improving Text-Image Alignment Evaluation","created":"2023-05-17","cited_by_count":108,"area":"mllm"},{"id":"2104.08455","title":"Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding","created":"2021-04-17","cited_by_count":106,"area":null},{"id":"2205.12854","title":"Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error Detectors","created":"2022-05-25","cited_by_count":104,"area":null},{"id":"2309.07852","title":"ExpertQA: Expert-Curated Questions and Attributed Answers","created":"2023-09-14","cited_by_count":97,"area":null},{"id":"2301.13298","title":"LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization","created":"2023-01-30","cited_by_count":96,"area":null},{"id":"2403.18771","title":"CheckEval: A reliable LLM-as-a-Judge framework for evaluating text generation using checklists","created":"2024-03-27","cited_by_count":94,"area":null},{"id":"2211.08412","title":"Evaluating the Factual Consistency of Large Language Models Through News Summarization","created":"2022-11-15","cited_by_count":92,"area":null},{"id":"2305.11171","title":"TrueTeacher: Learning Factual Consistency Evaluation with Large Language Models","created":"2023-05-18","cited_by_count":83,"area":null},{"id":"2407.00908","title":"FineSurE: Fine-grained Summarization Evaluation using LLMs","created":"2024-07-01","cited_by_count":83,"area":null},{"id":"2104.06486","title":"MS2: Multi-Document Summarization of Medical Studies","created":"2021-04-13","cited_by_count":80,"area":null},{"id":"2210.07700","title":"Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey","created":"2022-10-14","cited_by_count":80,"area":null},{"id":"2406.16264","title":"One Thousand and One Pairs: A \"novel\" challenge for long-context language models","created":"2024-06-24","cited_by_count":80,"area":null},{"id":"2104.14839","title":"The Factual Inconsistency Problem in Abstractive Text Summarization: A Survey","created":"2021-04-30","cited_by_count":79,"area":null},{"id":"2105.00071","title":"Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark","created":"2021-04-30","cited_by_count":77,"area":null},{"id":"2303.15621","title":"ChatGPT as a Factual Inconsistency Evaluator for Text Summarization","created":"2023-03-27","cited_by_count":75,"area":null},{"id":"2402.03190","title":"Unified Hallucination Detection for Multimodal Large Language Models","created":"2024-02-05","cited_by_count":75,"area":"mllm"},{"id":"2207.00939","title":"An Empirical Survey on Long Document Summarization: Datasets, Models and Metrics","created":"2022-07-03","cited_by_count":74,"area":null},{"id":"2407.10817","title":"Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluation","created":"2024-07-15","cited_by_count":74,"area":null},{"id":"2306.00186","title":"Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback","created":"2023-05-31","cited_by_count":72,"area":null},{"id":"2307.07889","title":"LLM Comparative Assessment: Zero-shot NLG Evaluation through Pairwise Comparisons using Large Language Models","created":"2023-07-15","cited_by_count":71,"area":null},{"id":"2312.17249","title":"Do Androids Know They're Only Dreaming of Electric Sheep?","created":"2023-12-28","cited_by_count":67,"area":"mechinterp"},{"id":"2205.06938","title":"Generating Literal and Implied Subquestions to Fact-check Complex Claims","created":"2022-05-14","cited_by_count":66,"area":null},{"id":"2310.00741","title":"FELM: Benchmarking Factuality Evaluation of Large Language Models","created":"2023-10-01","cited_by_count":66,"area":null},{"id":"2205.01883","title":"All You May Need for VQA are Image Captions","created":"2022-05-04","cited_by_count":65,"area":null},{"id":"2305.14564","title":"PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documents","created":"2023-05-23","cited_by_count":61,"area":"lr"},{"id":"2109.06379","title":"Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generation","created":"2021-09-14","cited_by_count":60,"area":null},{"id":"2105.04623","title":"Improving Factual Consistency of Abstractive Summarization via Question Answering","created":"2021-05-10","cited_by_count":55,"area":null},{"id":"2305.08281","title":"FactKB: Generalizable Factuality Evaluation using Language Models Enhanced with Factual Knowledge","created":"2023-05-14","cited_by_count":55,"area":null},{"id":"2309.13308","title":"Calibrating LLM-Based Evaluator","created":"2023-09-23","cited_by_count":53,"area":null},{"id":"2403.12027","title":"From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models","created":"2024-03-18","cited_by_count":53,"area":null},{"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":"2108.13684","title":"Faithful or Extractive? On Mitigating the Faithfulness-Abstractiveness Trade-off in Abstractive Summarization","created":"2021-08-31","cited_by_count":51,"area":null},{"id":"2401.17043","title":"CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models","created":"2024-01-30","cited_by_count":50,"area":"rag"},{"id":"2205.07830","title":"FactPEGASUS: Factuality-Aware Pre-training and Fine-tuning for Abstractive Summarization","created":"2022-05-16","cited_by_count":49,"area":null},{"id":"2212.10020","title":"On the Blind Spots of Model-Based Evaluation Metrics for Text Generation","created":"2022-12-20","cited_by_count":49,"area":null},{"id":"2210.06340","title":"Improving Radiology Report Generation Systems by Removing Hallucinated References to Non-existent Priors","created":"2022-09-27","cited_by_count":48,"area":null},{"id":"2203.00343","title":"Read before Generate! Faithful Long Form Question Answering with Machine Reading","created":"2022-03-01","cited_by_count":47,"area":null},{"id":"2310.01542","title":"Fusing Models with Complementary Expertise","created":"2023-10-02","cited_by_count":46,"area":null},{"id":"2107.03444","title":"Keep it Simple: Unsupervised Simplification of Multi-Paragraph Text","created":"2021-07-07","cited_by_count":45,"area":null},{"id":"2310.09044","title":"KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection","created":"2023-10-13","cited_by_count":45,"area":null},{"id":"2112.08713","title":"CONFIT: Toward Faithful Dialogue Summarization with Linguistically-Informed Contrastive Fine-tuning","created":"2021-12-16","cited_by_count":44,"area":null},{"id":"2207.00397","title":"Conditional Generation with a Question-Answering Blueprint","created":"2022-07-01","cited_by_count":44,"area":null},{"id":"2306.01200","title":"Multi-Dimensional Evaluation of Text Summarization with In-Context Learning","created":"2023-06-01","cited_by_count":44,"area":null},{"id":"2407.04121","title":"Hallucination Detection: Robustly Discerning Reliable Answers in Large Language Models","created":"2024-07-04","cited_by_count":44,"area":null},{"id":"2109.11503","title":"Finding a Balanced Degree of Automation for Summary Evaluation","created":"2021-09-23","cited_by_count":43,"area":null},{"id":"2310.07289","title":"Beyond Factuality: A Comprehensive Evaluation of Large Language Models as Knowledge Generators","created":"2023-10-11","cited_by_count":43,"area":null},{"id":"2312.05200","title":"DelucionQA: Detecting Hallucinations in Domain-specific Question Answering","created":"2023-12-08","cited_by_count":43,"area":null},{"id":"2105.14682","title":"Zero-shot Fact Verification by Claim Generation","created":"2021-05-31","cited_by_count":42,"area":null},{"id":"2212.10622","title":"mFACE: Multilingual Summarization with Factual Consistency Evaluation","created":"2022-12-20","cited_by_count":42,"area":null},{"id":"2305.13194","title":"SEAHORSE: A Multilingual, Multifaceted Dataset for Summarization Evaluation","created":"2023-05-22","cited_by_count":42,"area":null},{"id":"2204.06508","title":"FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representations","created":"2022-04-13","cited_by_count":41,"area":null},{"id":"2403.11903","title":"A Closer Look at Claim Decomposition","created":"2024-03-18","cited_by_count":41,"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":"2210.12378","title":"Correcting Diverse Factual Errors in Abstractive Summarization via Post-Editing and Language Model Infilling","created":"2022-10-22","cited_by_count":38,"area":null},{"id":"2212.09968","title":"On Improving Summarization Factual Consistency from Natural Language Feedback","created":"2022-12-20","cited_by_count":38,"area":"alignment"}],"next_cursor":"100"}