{"list":"other","total":64,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1803.05355","title":"FEVER: a large-scale dataset for Fact Extraction and VERification","created":"2018-03-14","cited_by_count":1375},{"id":"2005.00661","title":"On Faithfulness and Factuality in Abstractive Summarization","created":"2020-05-02","cited_by_count":900},{"id":"1902.01007","title":"Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference","created":"2019-02-04","cited_by_count":876},{"id":"2308.08747","title":"An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning","created":"2023-08-17","cited_by_count":639},{"id":"2402.00838","title":"OLMo: Accelerating the Science of Language Models","created":"2024-02-01","cited_by_count":613},{"id":"1910.12840","title":"Evaluating the Factual Consistency of Abstractive Text Summarization","created":"2019-10-28","cited_by_count":584},{"id":"2004.14974","title":"Fact or Fiction: Verifying Scientific Claims","created":"2020-04-30","cited_by_count":554},{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532},{"id":"1911.03429","title":"ERASER: A Benchmark to Evaluate Rationalized NLP Models","created":"2019-11-08","cited_by_count":530},{"id":"2402.00159","title":"Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research","created":"2024-01-31","cited_by_count":483},{"id":"1812.01193","title":"e-SNLI: Natural Language Inference with Natural Language Explanations","created":"2018-12-04","cited_by_count":468},{"id":"2009.10795","title":"Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics","created":"2020-09-22","cited_by_count":425},{"id":"1911.03891","title":"Social Bias Frames: Reasoning about Social and Power Implications of Language","created":"2019-11-10","cited_by_count":380},{"id":"2004.04228","title":"Asking and Answering Questions to Evaluate the Factual Consistency of Summaries","created":"2020-04-08","cited_by_count":378},{"id":"2310.18018","title":"NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark","created":"2023-10-27","cited_by_count":348},{"id":"1805.01042","title":"Hypothesis Only Baselines in Natural Language Inference","created":"2018-05-02","cited_by_count":295},{"id":"2205.05131","title":"UL2: Unifying Language Learning Paradigms","created":"2022-05-10","cited_by_count":295},{"id":"2209.01975","title":"Selective Annotation Makes Language Models Better Few-Shot Learners","created":"2022-09-05","cited_by_count":243},{"id":"2103.08541","title":"Get Your Vitamin C! Robust Fact Verification with Contrastive Evidence","created":"2021-03-15","cited_by_count":225},{"id":"2304.03439","title":"Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4","created":"2023-04-07","cited_by_count":202},{"id":"2012.00614","title":"CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims","created":"2020-12-01","cited_by_count":196},{"id":"2310.05470","title":"Generative Judge for Evaluating Alignment","created":"2023-10-09","cited_by_count":169},{"id":"2010.12762","title":"Measuring Association Between Labels and Free-Text Rationales","created":"2020-10-24","cited_by_count":160},{"id":"2402.00530","title":"Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning","created":"2024-02-01","cited_by_count":138},{"id":"2305.16938","title":"Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation","created":"2023-05-26","cited_by_count":136},{"id":"1909.06321","title":"End-to-End Bias Mitigation by Modelling Biases in Corpora","created":"2019-09-13","cited_by_count":128},{"id":"2112.08674","title":"Reframing Human-AI Collaboration for Generating Free-Text Explanations","created":"2021-12-16","cited_by_count":125},{"id":"2106.03794","title":"COVID-Fact: Fact Extraction and Verification of Real-World Claims on COVID-19 Pandemic","created":"2021-06-07","cited_by_count":100},{"id":"2111.08284","title":"Few-Shot Self-Rationalization with Natural Language Prompts","created":"2021-11-16","cited_by_count":83},{"id":"1810.05995","title":"BLEU is Not Suitable for the Evaluation of Text Simplification","created":"2018-10-14","cited_by_count":78},{"id":"1911.01214","title":"A Richly Annotated Corpus for Different Tasks in Automated Fact-Checking","created":"2019-10-29","cited_by_count":74},{"id":"2310.00752","title":"TIGERScore: Towards Building Explainable Metric for All Text Generation Tasks","created":"2023-10-01","cited_by_count":70},{"id":"2212.08620","title":"POTATO: The Portable Text Annotation Tool","created":"2022-12-16","cited_by_count":64},{"id":"2107.02331","title":"Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering","created":"2021-07-06","cited_by_count":62},{"id":"2203.12942","title":"Generating Data to Mitigate Spurious Correlations in Natural Language Inference Datasets","created":"2022-03-24","cited_by_count":54},{"id":"2104.04725","title":"Fool Me Twice: Entailment from Wikipedia Gamification","created":"2021-04-10","cited_by_count":50},{"id":"1904.11544","title":"Probing What Different NLP Tasks Teach Machines about Function Word Comprehension","created":"2019-04-25","cited_by_count":44},{"id":"1906.00363","title":"Does It Make Sense? And Why? A Pilot Study for Sense Making and Explanation","created":"2019-06-02","cited_by_count":43},{"id":"2310.14564","title":"Language Models Hallucinate, but May Excel at Fact Verification","created":"2023-10-23","cited_by_count":37},{"id":"1611.00601","title":"Ordinal Common-sense Inference","created":"2016-11-02","cited_by_count":35},{"id":"2010.10418","title":"ConjNLI: Natural Language Inference Over Conjunctive Sentences","created":"2020-10-20","cited_by_count":27},{"id":"2403.12776","title":"Automated Data Curation for Robust Language Model Fine-Tuning","created":"2024-03-19","cited_by_count":27},{"id":"2105.14167","title":"NeuralLog: Natural Language Inference with Joint Neural and Logical Reasoning","created":"2021-05-29","cited_by_count":25},{"id":"2407.19200","title":"On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs","created":"2024-07-27","cited_by_count":25},{"id":"2402.10532","title":"Properties and Challenges of LLM-Generated Explanations","created":"2024-02-16","cited_by_count":24},{"id":"2311.02805","title":"Tailoring Self-Rationalizers with Multi-Reward Distillation","created":"2023-11-06","cited_by_count":21},{"id":"2204.06644","title":"METRO: Efficient Denoising Pretraining of Large Scale Autoencoding Language Models with Model Generated Signals","created":"2022-04-13","cited_by_count":20},{"id":"2112.06204","title":"Few-Shot Out-of-Domain Transfer Learning of Natural Language Explanations in a Label-Abundant Setup","created":"2021-12-12","cited_by_count":16},{"id":"1710.02925","title":"Natural Language Inference from Multiple Premises","created":"2017-10-09","cited_by_count":13},{"id":"2210.13575","title":"Does Self-Rationalization Improve Robustness to Spurious Correlations?","created":"2022-10-24","cited_by_count":9},{"id":"2405.16820","title":"Laboratory-Scale AI: Open-Weight Models are Competitive with ChatGPT Even in Low-Resource Settings","created":"2024-05-27","cited_by_count":9},{"id":"2204.04991","title":"TRUE: Re-evaluating Factual Consistency Evaluation","created":"2022-04-11","cited_by_count":8},{"id":"2110.06223","title":"Investigating the Effect of Natural Language Explanations on Out-of-Distribution Generalization in Few-shot NLI","created":"2021-10-12","cited_by_count":7},{"id":"2306.03315","title":"Few Shot Rationale Generation using Self-Training with Dual Teachers","created":"2023-06-05","cited_by_count":3},{"id":"2405.09454","title":"Tell Me Why: Explainable Public Health Fact-Checking with Large Language Models","created":"2024-05-15","cited_by_count":3}],"next_cursor":null}