{"list":"other","total":55,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"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":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"1903.10676","title":"SciBERT: A Pretrained Language Model for Scientific Text","created":"2019-03-26","cited_by_count":1414},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055},{"id":"2305.14387","title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback","created":"2023-05-22","cited_by_count":748},{"id":"2305.01937","title":"Can Large Language Models Be an Alternative to Human Evaluations?","created":"2023-05-03","cited_by_count":734},{"id":"2304.07327","title":"OpenAssistant Conversations -- Democratizing Large Language Model Alignment","created":"2023-04-14","cited_by_count":721},{"id":"1808.07042","title":"CoQA: A Conversational Question Answering Challenge","created":"2018-08-21","cited_by_count":683},{"id":"1907.11932","title":"Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment","created":"2019-07-27","cited_by_count":671},{"id":"2310.08491","title":"Prometheus: Inducing Fine-grained Evaluation Capability in Language Models","created":"2023-10-12","cited_by_count":575},{"id":"1707.07328","title":"Adversarial Examples for Evaluating Reading Comprehension Systems","created":"2017-07-23","cited_by_count":571},{"id":"2004.14974","title":"Fact or Fiction: Verifying Scientific Claims","created":"2020-04-30","cited_by_count":554},{"id":"2405.01535","title":"Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models","created":"2024-05-02","cited_by_count":446},{"id":"1804.07998","title":"Generating Natural Language Adversarial Examples","created":"2018-04-21","cited_by_count":424},{"id":"2303.04048","title":"Is ChatGPT a Good NLG Evaluator? A Preliminary Study","created":"2023-03-07","cited_by_count":422},{"id":"2302.14520","title":"Large Language Models Are State-of-the-Art Evaluators of Translation Quality","created":"2023-02-28","cited_by_count":420},{"id":"1909.02622","title":"MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance","created":"2019-09-05","cited_by_count":418},{"id":"1803.06643","title":"The Web as a Knowledge-base for Answering Complex Questions","created":"2018-03-18","cited_by_count":410},{"id":"2401.08417","title":"Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation","created":"2024-01-16","cited_by_count":394},{"id":"1904.01557","title":"Analysing Mathematical Reasoning Abilities of Neural Models","created":"2019-04-02","cited_by_count":335},{"id":"2004.01970","title":"BAE: BERT-based Adversarial Examples for Text Classification","created":"2020-04-04","cited_by_count":316},{"id":"2305.15717","title":"The False Promise of Imitating Proprietary LLMs","created":"2023-05-25","cited_by_count":263},{"id":"2307.10928","title":"FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets","created":"2023-07-20","cited_by_count":201},{"id":"2407.13168","title":"SciCode: A Research Coding Benchmark Curated by Scientists","created":"2024-07-18","cited_by_count":178},{"id":"2103.06332","title":"Hurdles to Progress in Long-form Question Answering","created":"2021-03-10","cited_by_count":167},{"id":"2008.12009","title":"A Survey of Evaluation Metrics Used for NLG Systems","created":"2020-08-27","cited_by_count":164},{"id":"2308.00436","title":"SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning","created":"2023-08-01","cited_by_count":159},{"id":"2211.13308","title":"SciRepEval: A Multi-Format Benchmark for Scientific Document Representations","created":"2022-11-23","cited_by_count":129},{"id":"2502.01534","title":"Preference Leakage: A Contamination Problem in LLM-as-a-judge","created":"2025-02-03","cited_by_count":125},{"id":"2301.13298","title":"LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization","created":"2023-01-30","cited_by_count":96},{"id":"2206.15030","title":"Modern Question Answering Datasets and Benchmarks: A Survey","created":"2022-06-30","cited_by_count":23},{"id":"2207.10295","title":"Addressing Optimism Bias in Sequence Modeling for Reinforcement Learning","created":"2022-07-21","cited_by_count":22},{"id":"2303.13351","title":"DBLP-QuAD: A Question Answering Dataset over the DBLP Scholarly Knowledge Graph","created":"2023-03-23","cited_by_count":18},{"id":"2409.18812","title":"LLMs4Synthesis: Leveraging Large Language Models for Scientific Synthesis","created":"2024-09-27","cited_by_count":13},{"id":"2307.04683","title":"CORE-GPT: Combining Open Access research and large language models for credible, trustworthy question answering","created":"2023-07-06","cited_by_count":10},{"id":"2109.07403","title":"BERT is Robust! A Case Against Synonym-Based Adversarial Examples in Text Classification","created":"2021-09-15","cited_by_count":9},{"id":"2407.00110","title":"Chat AI: A Seamless Slurm-Native Solution for HPC-Based Services","created":"2024-06-27","cited_by_count":6},{"id":"2407.02977","title":"Large Language Models as Evaluators for Scientific Synthesis","created":"2024-07-03","cited_by_count":5}],"next_cursor":null}