{"list":"other","total":63,"rows":[{"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":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004},{"id":"2408.06292","title":"The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery","created":"2024-08-12","cited_by_count":1071},{"id":"2105.09938","title":"Measuring Coding Challenge Competence With APPS","created":"2021-05-20","cited_by_count":902},{"id":"2401.18059","title":"RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval","created":"2024-01-31","cited_by_count":532},{"id":"2009.10297","title":"CodeBLEU: a Method for Automatic Evaluation of Code Synthesis","created":"2020-09-22","cited_by_count":479},{"id":"2503.16419","title":"Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models","created":"2025-03-20","cited_by_count":464},{"id":"2401.07339","title":"CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges","created":"2024-01-14","cited_by_count":282},{"id":"2404.10774","title":"MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents","created":"2024-04-16","cited_by_count":257},{"id":"2402.08983","title":"SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding","created":"2024-02-14","cited_by_count":247},{"id":"2305.14259","title":"SciMON: Scientific Inspiration Machines Optimized for Novelty","created":"2023-05-23","cited_by_count":179},{"id":"2502.08235","title":"The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks","created":"2025-02-12","cited_by_count":152},{"id":"2405.03595","title":"GREEN: Generative Radiology Report Evaluation and Error Notation","created":"2024-05-06","cited_by_count":128},{"id":"2402.16438","title":"Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models","created":"2024-02-26","cited_by_count":126},{"id":"2204.00498","title":"Evaluating the Text-to-SQL Capabilities of Large Language Models","created":"2022-03-15","cited_by_count":101},{"id":"2212.10481","title":"Execution-Based Evaluation for Open-Domain Code Generation","created":"2022-12-20","cited_by_count":91},{"id":"2311.08526","title":"GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer","created":"2023-11-14","cited_by_count":88},{"id":"2409.19886","title":"RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models","created":"2024-09-30","cited_by_count":88},{"id":"2405.19856","title":"DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories","created":"2024-05-30","cited_by_count":72},{"id":"2503.21248","title":"ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition","created":"2025-03-27","cited_by_count":66},{"id":"2311.09835","title":"ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code","created":"2023-11-16","cited_by_count":65},{"id":"2406.16845","title":"RaTEScore: A Metric for Radiology Report Generation","created":"2024-06-24","cited_by_count":65},{"id":"2102.00176","title":"Can We Automate Scientific Reviewing?","created":"2021-01-30","cited_by_count":63},{"id":"2406.16253","title":"LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing","created":"2024-06-24","cited_by_count":62},{"id":"2402.10890","title":"When is Tree Search Useful for LLM Planning? It Depends on the Discriminator","created":"2024-02-16","cited_by_count":47},{"id":"2405.03279","title":"Lifelong Knowledge Editing for LLMs with Retrieval-Augmented Continuous Prompt Learning","created":"2024-05-06","cited_by_count":40},{"id":"2406.18406","title":"IRCAN: Mitigating Knowledge Conflicts in LLM Generation via Identifying and Reweighting Context-Aware Neurons","created":"2024-06-26","cited_by_count":38},{"id":"2305.04032","title":"ToolCoder: Teach Code Generation Models to use API search tools","created":"2023-05-06","cited_by_count":37},{"id":"2312.12141","title":"Neuron-Level Knowledge Attribution in Large Language Models","created":"2023-12-19","cited_by_count":37},{"id":"2308.08973","title":"End-to-End Beam Retrieval for Multi-Hop Question Answering","created":"2023-08-17","cited_by_count":35},{"id":"2406.12585","title":"Breaking the Ceiling of the LLM Community by Treating Token Generation as a Classification for Ensembling","created":"2024-06-18","cited_by_count":33},{"id":"2403.11996","title":"Accelerating Scientific Discovery with Generative Knowledge Extraction, Graph-Based Representation, and Multimodal Intelligent Graph Reasoning","created":"2024-03-18","cited_by_count":27},{"id":"2407.18698","title":"Adaptive Contrastive Search: Uncertainty-Guided Decoding for Open-Ended Text Generation","created":"2024-07-26","cited_by_count":27},{"id":"2409.06185","title":"Can Large Language Models Unlock Novel Scientific Research Ideas?","created":"2024-09-10","cited_by_count":24},{"id":"2410.00593","title":"Style-Specific Neurons for Steering LLMs in Text Style Transfer","created":"2024-10-01","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":"2405.17044","title":"Generating Interesting Scientific Ideas using Knowledge Graphs and LLMs: Evaluations with 100 Research Group Leaders","created":"2024-05-27","cited_by_count":22},{"id":"2306.14070","title":"SuperBench: A Super-Resolution Benchmark Dataset for Scientific Machine Learning","created":"2023-06-24","cited_by_count":18},{"id":"2412.14141","title":"LLMs can Realize Combinatorial Creativity: Generating Creative Ideas via LLMs for Scientific Research","created":"2024-12-18","cited_by_count":17},{"id":"2406.12608","title":"Bridging Local Details and Global Context in Text-Attributed Graphs","created":"2024-06-18","cited_by_count":15},{"id":"2312.04889","title":"KwaiAgents: Generalized Information-seeking Agent System with Large Language Models","created":"2023-12-08","cited_by_count":14},{"id":"2402.15637","title":"Addressing Order Sensitivity of In-Context Demonstration Examples in Causal Language Models","created":"2024-02-23","cited_by_count":12},{"id":"2405.01884","title":"Beyond Single-Event Extraction: Towards Efficient Document-Level Multi-Event Argument Extraction","created":"2024-05-03","cited_by_count":12},{"id":"2406.06263","title":"MaskLID: Code-Switching Language Identification through Iterative Masking","created":"2024-06-10","cited_by_count":11},{"id":"2409.12545","title":"Enhancing Knowledge Distillation of Large Language Models through Efficient Multi-Modal Distribution Alignment","created":"2024-09-19","cited_by_count":11},{"id":"2408.14866","title":"Advancing Adversarial Suffix Transfer Learning on Aligned Large Language Models","created":"2024-08-27","cited_by_count":10},{"id":"2311.03366","title":"Functional Overlap Reranking for Neural Code Generation","created":"2023-10-16","cited_by_count":9},{"id":"2405.09913","title":"TransMI: A Framework to Create Strong Baselines from Multilingual Pretrained Language Models for Transliterated Data","created":"2024-05-16","cited_by_count":9},{"id":"2409.19749","title":"NeuroMax: Enhancing Neural Topic Modeling via Maximizing Mutual Information and Group Topic Regularization","created":"2024-09-29","cited_by_count":9},{"id":"1711.03543","title":"DLPaper2Code: Auto-generation of Code from Deep Learning Research Papers","created":"2017-11-09","cited_by_count":8},{"id":"2410.24114","title":"Nearest Neighbor Normalization Improves Multimodal Retrieval","created":"2024-10-31","cited_by_count":7},{"id":"2406.03239","title":"Document-level Claim Extraction and Decontextualisation for Fact-Checking","created":"2024-06-05","cited_by_count":6},{"id":"2410.10858","title":"Reasoning Paths Optimization: Learning to Reason and Explore From Diverse Paths","created":"2024-10-07","cited_by_count":6},{"id":"2411.00873","title":"CleaR: Towards Robust and Generalized Parameter-Efficient Fine-Tuning for Noisy Label Learning","created":"2024-10-31","cited_by_count":6},{"id":"2411.13036","title":"Unsupervised Homography Estimation on Multimodal Image Pair via Alternating Optimization","created":"2024-11-20","cited_by_count":5},{"id":"2408.06603","title":"Simple but Effective Compound Geometric Operations for Temporal Knowledge Graph Completion","created":"2024-08-13","cited_by_count":3},{"id":"2402.03142","title":"Less is KEN: a Universal and Simple Non-Parametric Pruning Algorithm for Large Language Models","created":"2024-02-05","cited_by_count":2},{"id":"2405.20341","title":"From Zero to Hero: Cold-Start Anomaly Detection","created":"2024-05-30","cited_by_count":2},{"id":"2412.05028","title":"Unifying Dual-Space Embedding for Entity Alignment via Contrastive Learning","created":"2024-12-06","cited_by_count":2}],"next_cursor":null}