{"list":"other","total":55,"rows":[{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1808.08745","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","created":"2018-08-27","cited_by_count":1317},{"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},{"id":"2111.09543","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","created":"2021-11-18","cited_by_count":1254},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"2212.10511","title":"When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories","created":"2022-12-20","cited_by_count":1128},{"id":"1602.06023","title":"Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond","created":"2016-02-19","cited_by_count":812},{"id":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"2305.02301","title":"Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes","created":"2023-05-03","cited_by_count":737},{"id":"2007.12626","title":"SummEval: Re-evaluating Summarization Evaluation","created":"2020-07-24","cited_by_count":674},{"id":"1803.02324","title":"Annotation Artifacts in Natural Language Inference Data","created":"2018-03-06","cited_by_count":671},{"id":"1910.12840","title":"Evaluating the Factual Consistency of Abstractive Text Summarization","created":"2019-10-28","cited_by_count":584},{"id":"1907.09190","title":"ELI5: Long Form Question Answering","created":"2019-07-22","cited_by_count":575},{"id":"2301.13848","title":"Benchmarking Large Language Models for News Summarization","created":"2023-01-31","cited_by_count":445},{"id":"2111.09525","title":"SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization","created":"2021-11-18","cited_by_count":407},{"id":"2004.04228","title":"Asking and Answering Questions to Evaluate the Factual Consistency of Summaries","created":"2020-04-08","cited_by_count":378},{"id":"2309.05922","title":"A Survey of Hallucination in Large Foundation Models","created":"2023-09-12","cited_by_count":368},{"id":"2305.13534","title":"How Language Model Hallucinations Can Snowball","created":"2023-05-22","cited_by_count":311},{"id":"2212.09561","title":"Large Language Models are Better Reasoners with Self-Verification","created":"2022-12-19","cited_by_count":307},{"id":"2304.09848","title":"Evaluating Verifiability in Generative Search Engines","created":"2023-04-19","cited_by_count":303},{"id":"2305.16739","title":"AlignScore: Evaluating Factual Consistency with a Unified Alignment Function","created":"2023-05-26","cited_by_count":288},{"id":"2104.13346","title":"Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics","created":"2021-04-27","cited_by_count":287},{"id":"2210.08726","title":"RARR: Researching and Revising What Language Models Say, Using Language Models","created":"2022-10-17","cited_by_count":287},{"id":"2112.08542","title":"QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization","created":"2021-12-16","cited_by_count":236},{"id":"2305.14552","title":"Sources of Hallucination by Large Language Models on Inference Tasks","created":"2023-05-23","cited_by_count":169},{"id":"2203.16804","title":"BRIO: Bringing Order to Abstractive Summarization","created":"2022-03-31","cited_by_count":161},{"id":"2010.03532","title":"What Can We Learn from Collective Human Opinions on Natural Language Inference Data?","created":"2020-10-07","cited_by_count":153},{"id":"2307.16877","title":"Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering","created":"2023-07-31","cited_by_count":151},{"id":"2104.04302","title":"Annotating and Modeling Fine-grained Factuality in Summarization","created":"2021-04-09","cited_by_count":131},{"id":"2109.09784","title":"Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization","created":"2021-08-30","cited_by_count":129},{"id":"2010.05478","title":"Evaluating Factuality in Generation with Dependency-level Entailment","created":"2020-10-12","cited_by_count":122},{"id":"2109.09209","title":"CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization","created":"2021-09-19","cited_by_count":120},{"id":"2303.01432","title":"WiCE: Real-World Entailment for Claims in Wikipedia","created":"2023-03-02","cited_by_count":120},{"id":"2103.06410","title":"MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarization","created":"2021-03-11","cited_by_count":104},{"id":"2205.12854","title":"Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error Detectors","created":"2022-05-25","cited_by_count":104},{"id":"2102.05169","title":"Decontextualization: Making Sentences Stand-Alone","created":"2021-02-09","cited_by_count":102},{"id":"2305.17529","title":"MeetingBank: A Benchmark Dataset for Meeting Summarization","created":"2023-05-27","cited_by_count":84},{"id":"2106.09449","title":"DocNLI: A Large-scale Dataset for Document-level Natural Language Inference","created":"2021-06-17","cited_by_count":75},{"id":"2303.15621","title":"ChatGPT as a Factual Inconsistency Evaluator for Text Summarization","created":"2023-03-27","cited_by_count":75},{"id":"2402.13249","title":"TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization","created":"2024-02-20","cited_by_count":66},{"id":"2010.04529","title":"What Have We Achieved on Text Summarization?","created":"2020-10-09","cited_by_count":65},{"id":"2402.00559","title":"A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains","created":"2024-02-01","cited_by_count":65},{"id":"2306.00024","title":"Self-Verification Improves Few-Shot Clinical Information Extraction","created":"2023-05-30","cited_by_count":52},{"id":"2310.12150","title":"Understanding Retrieval Augmentation for Long-Form Question Answering","created":"2023-10-18","cited_by_count":45},{"id":"2305.06299","title":"Summarizing, Simplifying, and Synthesizing Medical Evidence Using GPT-3 (with Varying Success)","created":"2023-05-10","cited_by_count":40},{"id":"2104.00640","title":"AmbiFC: Fact-Checking Ambiguous Claims with Evidence","created":"2021-04-01","cited_by_count":38},{"id":"2310.14564","title":"Language Models Hallucinate, but May Excel at Fact Verification","created":"2023-10-23","cited_by_count":37},{"id":"2010.08580","title":"Linguistically-Informed Transformations (LIT): A Method for Automatically Generating Contrast Sets","created":"2020-10-16","cited_by_count":31},{"id":"2305.16519","title":"The Dangers of trusting Stochastic Parrots: Faithfulness and Trust in Open-domain Conversational Question Answering","created":"2023-05-25","cited_by_count":26},{"id":"2109.11020","title":"Exploring Decomposition for Table-based Fact Verification","created":"2021-09-22","cited_by_count":11},{"id":"2305.19339","title":"Less Likely Brainstorming: Using Language Models to Generate Alternative Hypotheses","created":"2023-05-30","cited_by_count":8}],"next_cursor":null}