{"list":"other","total":53,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"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":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"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":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"2111.09543","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","created":"2021-11-18","cited_by_count":1254},{"id":"1506.06724","title":"Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books","created":"2015-06-22","cited_by_count":1043},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841},{"id":"2311.16867","title":"The Falcon Series of Open Language Models","created":"2023-11-28","cited_by_count":535},{"id":"2302.06476","title":"Is ChatGPT a General-Purpose Natural Language Processing Task Solver?","created":"2023-02-08","cited_by_count":488},{"id":"2402.02716","title":"Understanding the planning of LLM agents: A survey","created":"2024-02-05","cited_by_count":421},{"id":"2206.10498","title":"PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change","created":"2022-06-21","cited_by_count":382},{"id":"2305.11747","title":"HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models","created":"2023-05-19","cited_by_count":341},{"id":"2309.01431","title":"Benchmarking Large Language Models in Retrieval-Augmented Generation","created":"2023-09-04","cited_by_count":312},{"id":"1908.05739","title":"Abductive Commonsense Reasoning","created":"2019-08-15","cited_by_count":301},{"id":"2402.00157","title":"Large Language Models for Mathematical Reasoning: Progresses and Challenges","created":"2024-01-31","cited_by_count":284},{"id":"2110.07178","title":"Symbolic Knowledge Distillation: from General Language Models to Commonsense Models","created":"2021-10-14","cited_by_count":270},{"id":"2010.05953","title":"COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs","created":"2020-10-12","cited_by_count":254},{"id":"2212.09597","title":"Reasoning with Language Model Prompting: A Survey","created":"2022-12-19","cited_by_count":252},{"id":"2303.05398","title":"MathPrompter: Mathematical Reasoning using Large Language Models","created":"2023-03-04","cited_by_count":236},{"id":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213},{"id":"2301.13808","title":"Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning","created":"2023-01-31","cited_by_count":178},{"id":"2212.01681","title":"Language Models as Agent Models","created":"2022-12-03","cited_by_count":132},{"id":"1709.08568","title":"The Consciousness Prior","created":"2017-09-25","cited_by_count":107},{"id":"2309.06794","title":"Cognitive Mirage: A Review of Hallucinations in Large Language Models","created":"2023-09-13","cited_by_count":84},{"id":"1912.05783","title":"CLOSURE: Assessing Systematic Generalization of CLEVR Models","created":"2019-12-12","cited_by_count":63},{"id":"2303.16421","title":"ChatGPT is a Knowledgeable but Inexperienced Solver: An Investigation of Commonsense Problem in Large Language Models","created":"2023-03-29","cited_by_count":63},{"id":"1805.06975","title":"Tracking State Changes in Procedural Text: A Challenge Dataset and Models for Process Paragraph Comprehension","created":"2018-05-17","cited_by_count":62},{"id":"2310.15747","title":"Large Language Models are Temporal and Causal Reasoners for Video Question Answering","created":"2023-10-24","cited_by_count":51},{"id":"2305.05252","title":"Distilling Script Knowledge from Large Language Models for Constrained Language Planning","created":"2023-05-09","cited_by_count":45},{"id":"2305.03695","title":"Vera: A General-Purpose Plausibility Estimation Model for Commonsense Statements","created":"2023-05-05","cited_by_count":44},{"id":"2306.08952","title":"Towards Benchmarking and Improving the Temporal Reasoning Capability of Large Language Models","created":"2023-06-15","cited_by_count":37},{"id":"1808.10012","title":"Reasoning about Actions and State Changes by Injecting Commonsense Knowledge","created":"2018-08-29","cited_by_count":29},{"id":"2306.16793","title":"Benchmarking Large Language Model Capabilities for Conditional Generation","created":"2023-06-29","cited_by_count":29},{"id":"2401.07286","title":"CANDLE: Iterative Conceptualization and Instantiation Distillation from Large Language Models for Commonsense Reasoning","created":"2024-01-14","cited_by_count":28},{"id":"2305.16572","title":"Counterfactual reasoning: Testing language models' understanding of hypothetical scenarios","created":"2023-05-26","cited_by_count":27},{"id":"2401.00690","title":"Benchmarking Large Language Models on Controllable Generation under Diversified Instructions","created":"2024-01-01","cited_by_count":27},{"id":"2101.00154","title":"DISCOS: Bridging the Gap between Discourse Knowledge and Commonsense Knowledge","created":"2021-01-01","cited_by_count":26},{"id":"2404.09127","title":"Confidence Calibration and Rationalization for LLMs via Multi-Agent Deliberation","created":"2024-04-14","cited_by_count":26},{"id":"2401.17585","title":"Propagation and Pitfalls: Reasoning-based Assessment of Knowledge Editing through Counterfactual Tasks","created":"2024-01-31","cited_by_count":24},{"id":"2211.08316","title":"FolkScope: Intention Knowledge Graph Construction for E-commerce Commonsense Discovery","created":"2022-11-15","cited_by_count":23},{"id":"2305.19068","title":"Complex Query Answering on Eventuality Knowledge Graph with Implicit Logical Constraints","created":"2023-05-30","cited_by_count":21},{"id":"2305.19213","title":"The Magic of IF: Investigating Causal Reasoning Abilities in Large Language Models of Code","created":"2023-05-30","cited_by_count":21},{"id":"2311.09174","title":"AbsPyramid: Benchmarking the Abstraction Ability of Language Models with a Unified Entailment Graph","created":"2023-11-15","cited_by_count":17},{"id":"2308.01906","title":"Reasoning in Large Language Models Through Symbolic Math Word Problems","created":"2023-08-03","cited_by_count":16},{"id":"2109.07679","title":"Benchmarking Commonsense Knowledge Base Population with an Effective Evaluation Dataset","created":"2021-09-16","cited_by_count":15},{"id":"2305.08677","title":"Natural Language Decomposition and Interpretation of Complex Utterances","created":"2023-05-15","cited_by_count":10}],"next_cursor":null}