{"list":"other","total":63,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2305.14325","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","created":"2023-05-23","cited_by_count":1784},{"id":"2305.01210","title":"Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation","created":"2023-05-02","cited_by_count":1391},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"2305.04388","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","created":"2023-05-07","cited_by_count":1122},{"id":"2305.19118","title":"Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate","created":"2023-05-30","cited_by_count":1011},{"id":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988},{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939},{"id":"1801.07243","title":"Personalizing Dialogue Agents: I have a dog, do you have pets too?","created":"2018-01-22","cited_by_count":828},{"id":"2306.08568","title":"WizardCoder: Empowering Code Large Language Models with Evol-Instruct","created":"2023-06-14","cited_by_count":733},{"id":"2301.00234","title":"A Survey on In-context Learning","created":"2022-12-31","cited_by_count":721},{"id":"2404.13076","title":"LLM Evaluators Recognize and Favor Their Own Generations","created":"2024-04-15","cited_by_count":686},{"id":"2305.03495","title":"Automatic Prompt Optimization with \"Gradient Descent\" and Beam Search","created":"2023-05-04","cited_by_count":653},{"id":"2308.09583","title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","created":"2023-08-18","cited_by_count":625},{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465},{"id":"2410.02736","title":"Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge","created":"2024-10-03","cited_by_count":368},{"id":"2103.00453","title":"Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP","created":"2021-02-28","cited_by_count":337},{"id":"2005.00796","title":"A Simple Language Model for Task-Oriented Dialogue","created":"2020-05-02","cited_by_count":332},{"id":"2405.00451","title":"Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning","created":"2024-05-01","cited_by_count":241},{"id":"2205.12689","title":"Large Language Models are Few-Shot Clinical Information Extractors","created":"2022-05-25","cited_by_count":207},{"id":"2212.08061","title":"On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning","created":"2022-12-15","cited_by_count":194},{"id":"2311.04076","title":"Do LLMs exhibit human-like response biases? A case study in survey design","created":"2023-11-07","cited_by_count":180},{"id":"2103.11790","title":"Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do","created":"2021-03-08","cited_by_count":178},{"id":"1812.07617","title":"Towards Deep Conversational Recommendations","created":"2018-12-18","cited_by_count":176},{"id":"2309.17012","title":"Benchmarking Cognitive Biases in Large Language Models as Evaluators","created":"2023-09-29","cited_by_count":150},{"id":"1905.05709","title":"Challenges in Building Intelligent Open-domain Dialog Systems","created":"2019-05-13","cited_by_count":147},{"id":"1907.06554","title":"Asking Clarifying Questions in Open-Domain Information-Seeking Conversations","created":"2019-07-15","cited_by_count":139},{"id":"2007.04032","title":"Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusion","created":"2020-07-08","cited_by_count":122},{"id":"1911.12011","title":"JEC-QA: A Legal-Domain Question Answering Dataset","created":"2019-11-27","cited_by_count":116},{"id":"2410.21333","title":"Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse","created":"2024-10-27","cited_by_count":109},{"id":"2002.09102","title":"Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems","created":"2020-02-21","cited_by_count":98},{"id":"2202.12299","title":"Capturing Failures of Large Language Models via Human Cognitive Biases","created":"2022-02-24","cited_by_count":98},{"id":"2403.18932","title":"Measuring Political Bias in Large Language Models: What Is Said and How It Is Said","created":"2024-03-27","cited_by_count":89},{"id":"2206.09363","title":"Towards Unified Conversational Recommender Systems via Knowledge-Enhanced Prompt Learning","created":"2022-06-19","cited_by_count":86},{"id":"2305.07972","title":"Trillion Dollar Words: A New Financial Dataset, Task & Market Analysis","created":"2023-05-13","cited_by_count":75},{"id":"2308.00225","title":"Instructed to Bias: Instruction-Tuned Language Models Exhibit Emergent Cognitive Bias","created":"2023-08-01","cited_by_count":53},{"id":"2005.11723","title":"Query Resolution for Conversational Search with Limited Supervision","created":"2020-05-24","cited_by_count":52},{"id":"2404.12670","title":"Towards Human-centered Proactive Conversational Agents","created":"2024-04-19","cited_by_count":49},{"id":"2402.08113","title":"Addressing cognitive bias in medical language models","created":"2024-02-12","cited_by_count":36},{"id":"2410.15413","title":"A Comprehensive Evaluation of Cognitive Biases in LLMs","created":"2024-10-20","cited_by_count":34},{"id":"2407.13647","title":"Weak-to-Strong Reasoning","created":"2024-07-18","cited_by_count":33},{"id":"2207.01056","title":"Counterfactually Measuring and Eliminating Social Bias in Vision-Language Pre-training Models","created":"2022-07-03","cited_by_count":28},{"id":"2409.16022","title":"AI Can Be Cognitively Biased: An Exploratory Study on Threshold Priming in LLM-Based Batch Relevance Assessment","created":"2024-09-24","cited_by_count":20},{"id":"2312.05762","title":"Multi-Defendant Legal Judgment Prediction via Hierarchical Reasoning","created":"2023-12-10","cited_by_count":19},{"id":"2401.18070","title":"Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners?","created":"2024-01-31","cited_by_count":19},{"id":"2107.05760","title":"Asking Clarifying Questions Based on Negative Feedback in Conversational Search","created":"2021-07-12","cited_by_count":12},{"id":"2112.05084","title":"A Survey on Echo Chambers on Social Media: Description, Detection and Mitigation","created":"2021-12-09","cited_by_count":12},{"id":"2004.14162","title":"Conversations with Search Engines: SERP-based Conversational Response Generation","created":"2020-04-29","cited_by_count":11},{"id":"2310.16738","title":"Improving Conversational Recommendation Systems via Bias Analysis and Language-Model-Enhanced Data Augmentation","created":"2023-10-25","cited_by_count":11},{"id":"2501.17969","title":"LLMs can be Fooled into Labelling a Document as Relevant (best caf\\'e near me; this paper is perfectly relevant)","created":"2025-01-29","cited_by_count":10},{"id":"2410.02897","title":"Cognitive Biases in Large Language Models for News Recommendation","created":"2024-10-03","cited_by_count":8},{"id":"2403.17286","title":"Cognitively Biased Users Interacting with Algorithmically Biased Results in Whole-Session Search on Debated Topics","created":"2024-03-26","cited_by_count":6},{"id":"2405.12480","title":"Towards Detecting and Mitigating Cognitive Bias in Spoken Conversational Search","created":"2024-05-21","cited_by_count":5},{"id":"2410.21529","title":"Can Users Detect Biases or Factual Errors in Generated Responses in Conversational Information-Seeking?","created":"2024-10-28","cited_by_count":5},{"id":"2409.00890","title":"Towards Investigating Biases in Spoken Conversational Search","created":"2024-09-02","cited_by_count":1}],"next_cursor":null}