{"total":272,"rows":[{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939,"area":null},{"id":"2305.08322","title":"C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models","created":"2023-05-15","cited_by_count":708,"area":null},{"id":"2306.09212","title":"CMMLU: Measuring massive multitask language understanding in Chinese","created":"2023-06-15","cited_by_count":449,"area":null},{"id":"2301.13848","title":"Benchmarking Large Language Models for News Summarization","created":"2023-01-31","cited_by_count":445,"area":null},{"id":"2304.13712","title":"Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond","created":"2023-04-26","cited_by_count":411,"area":null},{"id":"2302.09210","title":"How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation","created":"2023-02-18","cited_by_count":348,"area":null},{"id":"2307.09009","title":"How is ChatGPT's behavior changing over time?","created":"2023-07-18","cited_by_count":270,"area":null},{"id":"2301.07069","title":"Prompting Large Language Model for Machine Translation: A Case Study","created":"2023-01-17","cited_by_count":250,"area":null},{"id":"2305.03514","title":"Can Large Language Models Transform Computational Social Science?","created":"2023-04-12","cited_by_count":250,"area":null},{"id":"2302.10724","title":"ChatGPT: Jack of all trades, master of none","created":"2023-02-21","cited_by_count":204,"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":"2309.05196","title":"Does Writing with Language Models Reduce Content Diversity?","created":"2023-09-11","cited_by_count":192,"area":null},{"id":"2307.16877","title":"Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering","created":"2023-07-31","cited_by_count":151,"area":null},{"id":"2410.02660","title":"How to Train Long-Context Language Models (Effectively)","created":"2024-10-03","cited_by_count":146,"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":"2310.00785","title":"BooookScore: A systematic exploration of book-length summarization in the era of LLMs","created":"2023-10-01","cited_by_count":137,"area":null},{"id":"2410.02694","title":"HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly","created":"2024-10-03","cited_by_count":125,"area":null},{"id":"2305.18486","title":"A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets","created":"2023-05-29","cited_by_count":123,"area":null},{"id":"2302.08081","title":"Exploring the Limits of ChatGPT for Query or Aspect-based Text Summarization","created":"2023-02-16","cited_by_count":122,"area":null},{"id":"2305.11859","title":"Complex Claim Verification with Evidence Retrieved in the Wild","created":"2023-05-19","cited_by_count":110,"area":null},{"id":"2405.12819","title":"Large Language Models Meet NLP: A Survey","created":"2024-05-21","cited_by_count":103,"area":null},{"id":"2403.02901","title":"A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methods","created":"2024-03-05","cited_by_count":102,"area":null},{"id":"2306.04618","title":"Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations","created":"2023-06-07","cited_by_count":97,"area":null},{"id":"2302.11520","title":"Guiding Large Language Models via Directional Stimulus Prompting","created":"2023-02-22","cited_by_count":95,"area":null},{"id":"2403.18421","title":"BioMedLM: A 2.7B Parameter Language Model Trained On Biomedical Text","created":"2024-03-27","cited_by_count":86,"area":null},{"id":"2305.17529","title":"MeetingBank: A Benchmark Dataset for Meeting Summarization","created":"2023-05-27","cited_by_count":84,"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":"2305.14239","title":"On Learning to Summarize with Large Language Models as References","created":"2023-05-23","cited_by_count":80,"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":"2311.09184","title":"Benchmarking Generation and Evaluation Capabilities of Large Language Models for Instruction Controllable Summarization","created":"2023-11-15","cited_by_count":69,"area":null},{"id":"2305.14857","title":"BUFFET: Benchmarking Large Language Models for Few-shot Cross-lingual Transfer","created":"2023-05-24","cited_by_count":68,"area":null},{"id":"2402.13249","title":"TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization","created":"2024-02-20","cited_by_count":66,"area":null},{"id":"2303.15078","title":"Large Language Models are Diverse Role-Players for Summarization Evaluation","created":"2023-03-27","cited_by_count":62,"area":null},{"id":"2304.04193","title":"Extractive Summarization via ChatGPT for Faithful Summary Generation","created":"2023-04-09","cited_by_count":59,"area":null},{"id":"2407.00128","title":"When Search Engine Services meet Large Language Models: Visions and Challenges","created":"2024-06-28","cited_by_count":59,"area":null},{"id":"2410.18417","title":"Large Language Models Reflect the Ideology of their Creators","created":"2024-10-24","cited_by_count":57,"area":null},{"id":"2211.07634","title":"Follow the Wisdom of the Crowd: Effective Text Generation via Minimum Bayes Risk Decoding","created":"2022-11-14","cited_by_count":54,"area":null},{"id":"2212.09739","title":"LENS: A Learnable Evaluation Metric for Text Simplification","created":"2022-12-19","cited_by_count":54,"area":null},{"id":"2305.14835","title":"SummIt: Iterative Text Summarization via ChatGPT","created":"2023-05-24","cited_by_count":54,"area":null},{"id":"2309.04269","title":"From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting","created":"2023-09-08","cited_by_count":52,"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":"2307.15020","title":"SuperCLUE: A Comprehensive Chinese Large Language Model Benchmark","created":"2023-07-27","cited_by_count":50,"area":null},{"id":"2306.11816","title":"Learning to Generate Better Than Your LLM","created":"2023-06-20","cited_by_count":49,"area":null},{"id":"2310.15959","title":"NoteChat: A Dataset of Synthetic Doctor-Patient Conversations Conditioned on Clinical Notes","created":"2023-10-24","cited_by_count":48,"area":null},{"id":"2406.17744","title":"Following Length Constraints in Instructions","created":"2024-06-25","cited_by_count":46,"area":null},{"id":"2211.15914","title":"Prompted Opinion Summarization with GPT-3.5","created":"2022-11-29","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":"2309.09558","title":"Summarization is (Almost) Dead","created":"2023-09-18","cited_by_count":44,"area":null},{"id":"2305.06299","title":"Summarizing, Simplifying, and Synthesizing Medical Evidence Using GPT-3 (with Varying Success)","created":"2023-05-10","cited_by_count":40,"area":null},{"id":"2404.12726","title":"Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Works","created":"2024-04-19","cited_by_count":38,"area":null},{"id":"2406.04306","title":"Improving Uncertainty Estimation through Semantically Diverse Language Generation","created":"2024-06-06","cited_by_count":35,"area":null},{"id":"2310.19233","title":"Building Real-World Meeting Summarization Systems using Large Language Models: A Practical Perspective","created":"2023-10-30","cited_by_count":34,"area":null},{"id":"2402.06544","title":"Calibrating Long-form Generations from Large Language Models","created":"2024-02-09","cited_by_count":32,"area":null},{"id":"2305.16806","title":"Do GPTs Produce Less Literal Translations?","created":"2023-05-26","cited_by_count":30,"area":null},{"id":"2310.10570","title":"On Context Utilization in Summarization with Large Language Models","created":"2023-10-16","cited_by_count":30,"area":null},{"id":"2306.16793","title":"Benchmarking Large Language Model Capabilities for Conditional Generation","created":"2023-06-29","cited_by_count":29,"area":null},{"id":"2401.14280","title":"RomanSetu: Efficiently unlocking multilingual capabilities of Large Language Models via Romanization","created":"2024-01-25","cited_by_count":29,"area":null},{"id":"2401.01989","title":"Revisiting Zero-Shot Abstractive Summarization in the Era of Large Language Models from the Perspective of Position Bias","created":"2024-01-03","cited_by_count":28,"area":null},{"id":"2404.03381","title":"Learning to Plan and Generate Text with Citations","created":"2024-04-04","cited_by_count":28,"area":null},{"id":"2411.04075","title":"M3SciQA: A Multi-Modal Multi-Document Scientific QA Benchmark for Evaluating Foundation Models","created":"2024-11-06","cited_by_count":27,"area":null},{"id":"2211.15649","title":"Beyond Counting Datasets: A Survey of Multilingual Dataset Construction and Necessary Resources","created":"2022-11-28","cited_by_count":25,"area":null},{"id":"2406.03487","title":"Analyzing LLM Behavior in Dialogue Summarization: Unveiling Circumstantial Hallucination Trends","created":"2024-06-05","cited_by_count":25,"area":null},{"id":"2412.07951","title":"From Lived Experience to Insight: Unpacking the Psychological Risks of Using AI Conversational Agents","created":"2024-12-10","cited_by_count":25,"area":null},{"id":"2310.10623","title":"Generating Summaries with Controllable Readability Levels","created":"2023-10-16","cited_by_count":24,"area":null},{"id":"2310.13014","title":"Large Language Model Prediction Capabilities: Evidence from a Real-World Forecasting Tournament","created":"2023-10-17","cited_by_count":24,"area":null},{"id":"2405.00982","title":"On the Evaluation of Machine-Generated Reports","created":"2024-05-02","cited_by_count":23,"area":null},{"id":"2303.03283","title":"The AI Ghostwriter Effect: When Users Do Not Perceive Ownership of AI-Generated Text But Self-Declare as Authors","created":"2023-03-06","cited_by_count":22,"area":null},{"id":"2408.04211","title":"MMREC: LLM Based Multi-Modal Recommender System","created":"2024-08-08","cited_by_count":22,"area":null},{"id":"2410.23609","title":"On Positional Bias of Faithfulness for Long-form Summarization","created":"2024-10-31","cited_by_count":22,"area":null},{"id":"2210.12152","title":"WikiWhy: Answering and Explaining Cause-and-Effect Questions","created":"2022-10-21","cited_by_count":21,"area":null},{"id":"2402.07862","title":"AI-Augmented Predictions: LLM Assistants Improve Human Forecasting Accuracy","created":"2024-02-12","cited_by_count":21,"area":null},{"id":"2407.03658","title":"GPT-4 vs. Human Translators: A Comprehensive Evaluation of Translation Quality Across Languages, Domains, and Expertise Levels","created":"2024-07-04","cited_by_count":21,"area":null},{"id":"2212.10526","title":"Open Domain Multi-document Summarization: A Comprehensive Study of Model Brittleness under Retrieval","created":"2022-12-20","cited_by_count":20,"area":null},{"id":"2302.01328","title":"IC3: Image Captioning by Committee Consensus","created":"2023-02-02","cited_by_count":20,"area":null},{"id":"2310.05015","title":"Compresso: Structured Pruning with Collaborative Prompting Learns Compact Large Language Models","created":"2023-10-08","cited_by_count":19,"area":null},{"id":"2403.01061","title":"Reading Subtext: Evaluating Large Language Models on Short Story Summarization with Writers","created":"2024-03-02","cited_by_count":19,"area":null},{"id":"2406.10278","title":"Prompt-Based Length Controlled Generation with Multiple Control Types","created":"2024-06-12","cited_by_count":19,"area":null},{"id":"2305.11828","title":"Appraising the Potential Uses and Harms of LLMs for Medical Systematic Reviews","created":"2023-05-19","cited_by_count":18,"area":null},{"id":"2305.13693","title":"Automated Metrics for Medical Multi-Document Summarization Disagree with Human Evaluations","created":"2023-05-23","cited_by_count":18,"area":null},{"id":"2309.08047","title":"Bias in News Summarization: Measures, Pitfalls and Corpora","created":"2023-09-14","cited_by_count":18,"area":null},{"id":"2402.11456","title":"FactPICO: Factuality Evaluation for Plain Language Summarization of Medical Evidence","created":"2024-02-18","cited_by_count":18,"area":null},{"id":"2212.10449","title":"Socratic Pretraining: Question-Driven Pretraining for Controllable Summarization","created":"2022-12-20","cited_by_count":17,"area":null},{"id":"2311.07884","title":"Fair Abstractive Summarization of Diverse Perspectives","created":"2023-11-14","cited_by_count":17,"area":null},{"id":"2302.14229","title":"Zero-Shot Cross-Lingual Summarization via Large Language Models","created":"2023-02-28","cited_by_count":16,"area":null},{"id":"2305.14702","title":"DecipherPref: Analyzing Influential Factors in Human Preference Judgments via GPT-4","created":"2023-05-24","cited_by_count":16,"area":null},{"id":"2211.09783","title":"UniSumm and SummZoo: Unified Model and Diverse Benchmark for Few-Shot Summarization","created":"2022-11-17","cited_by_count":15,"area":null},{"id":"2305.14341","title":"APPLS: Evaluating Evaluation Metrics for Plain Language Summarization","created":"2023-05-23","cited_by_count":15,"area":null},{"id":"2305.14458","title":"Dancing Between Success and Failure: Edit-level Simplification Evaluation using SALSA","created":"2023-05-23","cited_by_count":15,"area":null},{"id":"2404.04204","title":"Social Skill Training with Large Language Models","created":"2024-04-05","cited_by_count":15,"area":null},{"id":"2407.02039","title":"Prompt Stability Scoring for Text Annotation with Large Language Models","created":"2024-07-02","cited_by_count":15,"area":null},{"id":"2407.10078","title":"Data Imputation using Large Language Model to Accelerate Recommendation System","created":"2024-07-14","cited_by_count":15,"area":null},{"id":"2408.08978","title":"See What LLMs Cannot Answer: A Self-Challenge Framework for Uncovering LLM Weaknesses","created":"2024-08-16","cited_by_count":15,"area":null},{"id":"2303.03948","title":"A Meta-Evaluation of Faithfulness Metrics for Long-Form Hospital-Course Summarization","created":"2023-03-07","cited_by_count":14,"area":null},{"id":"2305.14647","title":"Scientific Opinion Summarization: Paper Meta-review Generation Dataset, Methods, and Evaluation","created":"2023-05-24","cited_by_count":14,"area":null},{"id":"2308.12030","title":"Prompt-Based Length Controlled Generation with Reinforcement Learning","created":"2023-08-23","cited_by_count":14,"area":null},{"id":"2310.10706","title":"Harnessing the Power of LLMs: Evaluating Human-AI Text Co-Creation through the Lens of News Headline Generation","created":"2023-10-16","cited_by_count":14,"area":null},{"id":"2405.06524","title":"Prompting Large Language Models with Knowledge Graphs for Question Answering Involving Long-tail Facts","created":"2024-05-10","cited_by_count":14,"area":null},{"id":"2411.13032","title":"\"It was 80% me, 20% AI\": Seeking Authenticity in Co-Writing with Large Language Models","created":"2024-11-20","cited_by_count":14,"area":null},{"id":"2211.05041","title":"MACSum: Controllable Summarization with Mixed Attributes","created":"2022-11-09","cited_by_count":13,"area":null},{"id":"2306.17384","title":"SummQA at MEDIQA-Chat 2023:In-Context Learning with GPT-4 for Medical Summarization","created":"2023-06-30","cited_by_count":13,"area":null}],"next_cursor":"100"}