{"list":"other","total":55,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2303.16634","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","created":"2023-03-29","cited_by_count":2276},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2303.17760","title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","created":"2023-03-31","cited_by_count":1395},{"id":"2305.17926","title":"Large Language Models are not Fair Evaluators","created":"2023-05-29","cited_by_count":1085},{"id":"2305.19118","title":"Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate","created":"2023-05-30","cited_by_count":1011},{"id":"2308.07201","title":"ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate","created":"2023-08-14","cited_by_count":742},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"id":"2304.03277","title":"Instruction Tuning with GPT-4","created":"2023-04-06","cited_by_count":686},{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639},{"id":"2301.07597","title":"How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection","created":"2023-01-18","cited_by_count":481},{"id":"2005.00700","title":"UnifiedQA: Crossing Format Boundaries With a Single QA System","created":"2020-05-02","cited_by_count":476},{"id":"2010.12421","title":"TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification","created":"2020-10-23","cited_by_count":417},{"id":"2212.09689","title":"Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor","created":"2022-12-19","cited_by_count":397},{"id":"2303.11156","title":"Can AI-Generated Text be Reliably Detected?","created":"2023-03-17","cited_by_count":386},{"id":"1911.03891","title":"Social Bias Frames: Reasoning about Social and Power Implications of Language","created":"2019-11-10","cited_by_count":380},{"id":"2305.17493","title":"The Curse of Recursion: Training on Generated Data Makes Models Forget","created":"2023-05-27","cited_by_count":356},{"id":"2309.13007","title":"ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs","created":"2023-09-22","cited_by_count":309},{"id":"2011.00620","title":"Social Chemistry 101: Learning to Reason about Social and Moral Norms","created":"2020-11-01","cited_by_count":255},{"id":"2307.05300","title":"Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration","created":"2023-07-11","cited_by_count":251},{"id":"1803.06535","title":"Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfer","created":"2018-03-17","cited_by_count":211},{"id":"2212.10450","title":"Is GPT-3 a Good Data Annotator?","created":"2022-12-20","cited_by_count":208},{"id":"2304.05613","title":"ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning","created":"2023-04-12","cited_by_count":206},{"id":"2108.13487","title":"Want To Reduce Labeling Cost? GPT-3 Can Help","created":"2021-08-30","cited_by_count":196},{"id":"2304.10149","title":"Is ChatGPT a Good Recommender? A Preliminary Study","created":"2023-04-20","cited_by_count":193},{"id":"2309.13788","title":"Can LLM-Generated Misinformation Be Detected?","created":"2023-09-25","cited_by_count":177},{"id":"2306.04181","title":"Benchmarking Foundation Models with Language-Model-as-an-Examiner","created":"2023-06-07","cited_by_count":172},{"id":"2305.14552","title":"Sources of Hallucination by Large Language Models on Inference Tasks","created":"2023-05-23","cited_by_count":169},{"id":"2309.17012","title":"Benchmarking Cognitive Biases in Large Language Models as Evaluators","created":"2023-09-29","cited_by_count":150},{"id":"2305.13242","title":"MAGE: Machine-generated Text Detection in the Wild","created":"2023-05-22","cited_by_count":132},{"id":"2110.05699","title":"On Releasing Annotator-Level Labels and Information in Datasets","created":"2021-10-12","cited_by_count":126},{"id":"2304.02554","title":"Human-like Summarization Evaluation with ChatGPT","created":"2023-04-05","cited_by_count":126},{"id":"2306.01943","title":"NLPositionality: Characterizing Design Biases of Datasets and Models","created":"2023-06-02","cited_by_count":94},{"id":"2305.06626","title":"When the Majority is Wrong: Modeling Annotator Disagreement for Subjective Tasks","created":"2023-05-11","cited_by_count":90},{"id":"2311.16822","title":"Large Language Models Suffer From Their Own Output: An Analysis of the Self-Consuming Training Loop","created":"2023-11-28","cited_by_count":79},{"id":"2012.15349","title":"DynaSent: A Dynamic Benchmark for Sentiment Analysis","created":"2020-12-30","cited_by_count":63},{"id":"2304.11085","title":"Testing the Reliability of ChatGPT for Text Annotation and Classification: A Cautionary Remark","created":"2023-04-17","cited_by_count":54},{"id":"2301.05036","title":"Everyone's Voice Matters: Quantifying Annotation Disagreement Using Demographic Information","created":"2023-01-12","cited_by_count":52},{"id":"2304.14317","title":"ICE-Score: Instructing Large Language Models to Evaluate Code","created":"2023-04-27","cited_by_count":52},{"id":"2304.13861","title":"The Parrot Dilemma: Human-Labeled vs. LLM-augmented Data in Classification Tasks","created":"2023-04-26","cited_by_count":35},{"id":"2211.01786","title":"Crosslingual Generalization through Multitask Finetuning","created":"2022-11-03","cited_by_count":26},{"id":"2109.02738","title":"Does BERT Learn as Humans Perceive? Understanding Linguistic Styles through Lexica","created":"2021-09-06","cited_by_count":23},{"id":"2311.09799","title":"How Far Can We Extract Diverse Perspectives from Large Language Models?","created":"2023-11-16","cited_by_count":22},{"id":"2304.01196","title":"Baize: An Open-Source Chat Model with Parameter-Efficient Tuning on Self-Chat Data","created":"2023-04-03","cited_by_count":13},{"id":"2112.07475","title":"Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks","created":"2021-12-14","cited_by_count":12},{"id":"2306.02294","title":"Exposing Bias in Online Communities through Large-Scale Language Models","created":"2023-06-04","cited_by_count":5},{"id":"2211.13196","title":"SeedBERT: Recovering Annotator Rating Distributions from an Aggregated Label","created":"2022-11-23","cited_by_count":3},{"id":"2305.15070","title":"Annotation Imputation to Individualize Predictions: Initial Studies on Distribution Dynamics and Model Predictions","created":"2023-05-24","cited_by_count":2}],"next_cursor":null}