{"list":"other","total":62,"rows":[{"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":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"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":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"2306.06070","title":"Mind2Web: Towards a Generalist Agent for the Web","created":"2023-06-09","cited_by_count":1242},{"id":"2311.07911","title":"Instruction-Following Evaluation for Large Language Models","created":"2023-11-14","cited_by_count":1228},{"id":"2404.07972","title":"OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments","created":"2024-04-11","cited_by_count":1195},{"id":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100},{"id":"2501.17161","title":"SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training","created":"2025-01-28","cited_by_count":672},{"id":"2310.11667","title":"SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents","created":"2023-10-18","cited_by_count":367},{"id":"2310.12823","title":"AgentTuning: Enabling Generalized Agent Abilities for LLMs","created":"2023-10-19","cited_by_count":338},{"id":"1806.11532","title":"TextWorld: A Learning Environment for Text-based Games","created":"2018-06-29","cited_by_count":310},{"id":"2309.10691","title":"MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback","created":"2023-09-19","cited_by_count":297},{"id":"2404.19733","title":"Iterative Reasoning Preference Optimization","created":"2024-04-30","cited_by_count":246},{"id":"2004.10151","title":"Experience Grounds Language","created":"2020-04-21","cited_by_count":242},{"id":"2402.06457","title":"V-STaR: Training Verifiers for Self-Taught Reasoners","created":"2024-02-09","cited_by_count":217},{"id":"2006.13760","title":"The NetHack Learning Environment","created":"2020-06-24","cited_by_count":198},{"id":"2411.13543","title":"BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games","created":"2024-11-20","cited_by_count":146},{"id":"2308.04014","title":"Continual Pre-Training of Large Language Models: How to (re)warm your model?","created":"2023-08-08","cited_by_count":137},{"id":"2502.21321","title":"LLM Post-Training: A Deep Dive into Reasoning Large Language Models","created":"2025-02-28","cited_by_count":135},{"id":"2406.04520","title":"NATURAL PLAN: Benchmarking LLMs on Natural Language Planning","created":"2024-06-06","cited_by_count":128},{"id":"2310.01557","title":"SmartPlay: A Benchmark for LLMs as Intelligent Agents","created":"2023-10-02","cited_by_count":125},{"id":"2402.12348","title":"GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations","created":"2024-02-19","cited_by_count":120},{"id":"2406.04151","title":"AgentGym: Evolving Large Language Model-based Agents across Diverse Environments","created":"2024-06-06","cited_by_count":120},{"id":"2005.00955","title":"How Can We Accelerate Progress Towards Human-like Linguistic Generalization?","created":"2020-05-03","cited_by_count":114},{"id":"2312.04350","title":"CLadder: Assessing Causal Reasoning in Language Models","created":"2023-12-07","cited_by_count":107},{"id":"2305.08844","title":"RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs","created":"2023-05-15","cited_by_count":105},{"id":"2208.07998","title":"What Artificial Neural Networks Can Tell Us About Human Language Acquisition","created":"2022-08-17","cited_by_count":99},{"id":"2502.12118","title":"Scaling Test-Time Compute Without Verification or RL is Suboptimal","created":"2025-02-17","cited_by_count":84},{"id":"2404.10642","title":"Self-playing Adversarial Language Game Enhances LLM Reasoning","created":"2024-04-16","cited_by_count":83},{"id":"2312.06281","title":"EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models","created":"2023-12-11","cited_by_count":80},{"id":"2212.06801","title":"A fine-grained comparison of pragmatic language understanding in humans and language models","created":"2022-12-13","cited_by_count":70},{"id":"1804.03980","title":"Emergent Communication through Negotiation","created":"2018-04-11","cited_by_count":62},{"id":"2301.11796","title":"Call for Papers -- The BabyLM Challenge: Sample-efficient pretraining on a developmentally plausible corpus","created":"2023-01-27","cited_by_count":62},{"id":"2410.13648","title":"SimpleToM: Exposing the Gap between Explicit ToM Inference and Implicit ToM Application in LLMs","created":"2024-10-17","cited_by_count":57},{"id":"2305.13455","title":"Clembench: Using Game Play to Evaluate Chat-Optimized Language Models as Conversational Agents","created":"2023-05-22","cited_by_count":54},{"id":"2308.10032","title":"GameEval: Evaluating LLMs on Conversational Games","created":"2023-08-19","cited_by_count":37},{"id":"2309.04369","title":"Beyond Static Datasets: A Deep Interaction Approach to LLM Evaluation","created":"2023-09-08","cited_by_count":24},{"id":"2502.10645","title":"BabyLM Turns 3: Call for papers for the 2025 BabyLM workshop","created":"2025-02-15","cited_by_count":24},{"id":"2406.17453","title":"Learning to Ask Informative Questions: Enhancing LLMs with Preference Optimization and Expected Information Gain","created":"2024-06-25","cited_by_count":21},{"id":"2304.07007","title":"Dialogue Games for Benchmarking Language Understanding: Motivation, Taxonomy, Strategy","created":"2023-04-14","cited_by_count":12},{"id":"2405.13828","title":"Babysit A Language Model From Scratch: Interactive Language Learning by Trials and Demonstrations","created":"2024-05-22","cited_by_count":12},{"id":"2502.14359","title":"Triangulating LLM Progress through Benchmarks, Games, and Cognitive Tests","created":"2025-02-20","cited_by_count":12},{"id":"2408.15992","title":"CoGen: Learning from Feedback with Coupled Comprehension and Generation","created":"2024-08-28","cited_by_count":7},{"id":"2410.24218","title":"Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use","created":"2024-10-31","cited_by_count":7},{"id":"1908.10747","title":"Language Tasks and Language Games: On Methodology in Current Natural Language Processing Research","created":"2019-08-28","cited_by_count":6},{"id":"2410.13852","title":"Retrospective Learning from Interactions","created":"2024-10-17","cited_by_count":6},{"id":"2409.14247","title":"Repairs in a Block World: A New Benchmark for Handling User Corrections with Multi-Modal Language Models","created":"2024-09-21","cited_by_count":3},{"id":"2312.02431","title":"Visually Grounded Language Learning: a review of language games, datasets, tasks, and models","created":"2023-12-05","cited_by_count":2},{"id":"2403.17497","title":"Sharing the Cost of Success: A Game for Evaluating and Learning Collaborative Multi-Agent Instruction Giving and Following Policies","created":"2024-03-26","cited_by_count":2},{"id":"1707.02230","title":"Computational Models of Tutor Feedback in Language Acquisition","created":"2017-07-07","cited_by_count":1}],"next_cursor":null}