{"list":"other","total":62,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2207.01206","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","created":"2022-07-04","cited_by_count":1251},{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"id":"2211.00593","title":"Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small","created":"2022-11-01","cited_by_count":1165},{"id":"2112.00114","title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","created":"2021-11-30","cited_by_count":886},{"id":"1606.07947","title":"Sequence-Level Knowledge Distillation","created":"2016-06-25","cited_by_count":801},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"2212.07677","title":"Transformers learn in-context by gradient descent","created":"2022-12-15","cited_by_count":732},{"id":"2208.01066","title":"What Can Transformers Learn In-Context? A Case Study of Simple Function Classes","created":"2022-08-01","cited_by_count":715},{"id":"2211.15661","title":"What learning algorithm is in-context learning? Investigations with linear models","created":"2022-11-28","cited_by_count":684},{"id":"2304.15004","title":"Are Emergent Abilities of Large Language Models a Mirage?","created":"2023-04-28","cited_by_count":523},{"id":"2306.09927","title":"Trained Transformers Learn Linear Models In-Context","created":"2023-06-16","cited_by_count":337},{"id":"2306.04637","title":"Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection","created":"2023-06-07","cited_by_count":298},{"id":"2301.07067","title":"Transformers as Algorithms: Generalization and Stability in In-context Learning","created":"2023-01-17","cited_by_count":222},{"id":"2311.01460","title":"Implicit Chain of Thought Reasoning via Knowledge Distillation","created":"2023-11-02","cited_by_count":176},{"id":"2407.06023","title":"Distilling System 2 into System 1","created":"2024-07-08","cited_by_count":159},{"id":"2306.14050","title":"Symbolic Chain-of-Thought Distillation: Small Models Can Also \"Think\" Step-by-Step","created":"2023-06-24","cited_by_count":148},{"id":"2502.09597","title":"Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs","created":"2025-02-13","cited_by_count":148},{"id":"2106.06087","title":"Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models","created":"2021-06-10","cited_by_count":131},{"id":"2306.12672","title":"From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought","created":"2023-06-22","cited_by_count":119},{"id":"2207.10342","title":"Language Model Cascades","created":"2022-07-21","cited_by_count":107},{"id":"2305.01879","title":"SCOTT: Self-Consistent Chain-of-Thought Distillation","created":"2023-05-03","cited_by_count":105},{"id":"2403.19154","title":"STaR-GATE: Teaching Language Models to Ask Clarifying Questions","created":"2024-03-28","cited_by_count":104},{"id":"2310.11589","title":"Eliciting Human Preferences with Language Models","created":"2023-10-17","cited_by_count":92},{"id":"2310.10616","title":"How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations","created":"2023-10-16","cited_by_count":75},{"id":"2305.19165","title":"Strategic Reasoning with Language Models","created":"2023-05-30","cited_by_count":64},{"id":"2109.05794","title":"Building and Evaluating Open-Domain Dialogue Corpora with Clarifying Questions","created":"2021-09-13","cited_by_count":63},{"id":"2105.06965","title":"Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction","created":"2021-05-14","cited_by_count":59},{"id":"2406.17055","title":"Large Language Models Assume People are More Rational than We Really are","created":"2024-06-24","cited_by_count":54},{"id":"2204.02515","title":"Inferring Rewards from Language in Context","created":"2022-04-05","cited_by_count":50},{"id":"2305.13264","title":"Prompting is not a substitute for probability measurements in large language models","created":"2023-05-22","cited_by_count":44},{"id":"2412.03782","title":"The broader spectrum of in-context learning","created":"2024-12-05","cited_by_count":35},{"id":"2403.05534","title":"Bayesian Preference Elicitation with Language Models","created":"2024-03-08","cited_by_count":34},{"id":"2305.16635","title":"Impossible Distillation: from Low-Quality Model to High-Quality Dataset & Model for Summarization and Paraphrasing","created":"2023-05-26","cited_by_count":31},{"id":"2401.16646","title":"Incoherent Probability Judgments in Large Language Models","created":"2024-01-30","cited_by_count":30},{"id":"2312.12009","title":"Active Preference Inference using Language Models and Probabilistic Reasoning","created":"2023-12-19","cited_by_count":29},{"id":"2404.09911","title":"ChatShop: Interactive Information Seeking with Language Agents","created":"2024-04-15","cited_by_count":24},{"id":"2403.03348","title":"Learning to Maximize Mutual Information for Chain-of-Thought Distillation","created":"2024-03-05","cited_by_count":23},{"id":"2306.02797","title":"Human-like Few-Shot Learning via Bayesian Reasoning over Natural Language","created":"2023-06-05","cited_by_count":22},{"id":"2311.00445","title":"A Systematic Comparison of Syllogistic Reasoning in Humans and Language Models","created":"2023-11-01","cited_by_count":20},{"id":"2407.15814","title":"Perceptions of Linguistic Uncertainty by Language Models and Humans","created":"2024-07-22","cited_by_count":15},{"id":"2310.15151","title":"Verb Conjugation in Transformers Is Determined by Linear Encodings of Subject Number","created":"2023-10-23","cited_by_count":12},{"id":"2402.19471","title":"Loose LIPS Sink Ships: Asking Questions in Battleship with Language-Informed Program Sampling","created":"2024-02-29","cited_by_count":12},{"id":"2402.10416","title":"Grounding Language about Belief in a Bayesian Theory-of-Mind","created":"2024-02-16","cited_by_count":8},{"id":"2405.14769","title":"Pragmatic Feature Preferences: Learning Reward-Relevant Preferences from Human Input","created":"2024-05-23","cited_by_count":8}],"next_cursor":null}