{"list":"other","total":65,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"2506.05176","title":"Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models","created":"2025-06-05","cited_by_count":1261},{"id":"2405.04434","title":"DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model","created":"2024-05-07","cited_by_count":1135},{"id":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819},{"id":"2305.14975","title":"Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback","created":"2023-05-24","cited_by_count":812},{"id":"2303.08896","title":"SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models","created":"2023-03-15","cited_by_count":810},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"2205.14334","title":"Teaching Models to Express Their Uncertainty in Words","created":"2022-05-28","cited_by_count":751},{"id":"2210.07316","title":"MTEB: Massive Text Embedding Benchmark","created":"2022-10-13","cited_by_count":640},{"id":"1904.01685","title":"Measuring Calibration in Deep Learning","created":"2019-04-02","cited_by_count":446},{"id":"2308.10620","title":"Large Language Models for Software Engineering: A Systematic Literature Review","created":"2023-08-21","cited_by_count":399},{"id":"1909.10155","title":"Verified Uncertainty Calibration","created":"2019-09-23","cited_by_count":309},{"id":"2001.02114","title":"Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Making","created":"2020-01-07","cited_by_count":281},{"id":"2206.15000","title":"Grounded Copilot: How Programmers Interact with Code-Generating Models","created":"2022-06-30","cited_by_count":218},{"id":"2102.10395","title":"On Calibration and Out-of-domain Generalization","created":"2021-02-20","cited_by_count":134},{"id":"2304.00385","title":"Keep the Conversation Going: Fixing 162 out of 337 bugs for $0.42 each using ChatGPT","created":"2023-04-01","cited_by_count":125},{"id":"2012.08668","title":"Mitigating Bias in Calibration Error Estimation","created":"2020-12-15","cited_by_count":101},{"id":"2203.09095","title":"Automating Code Review Activities by Large-Scale Pre-training","created":"2022-03-17","cited_by_count":98},{"id":"2302.05020","title":"Impact of Code Language Models on Automated Program Repair","created":"2023-02-10","cited_by_count":85},{"id":"2303.17125","title":"A Large-Scale Survey on the Usability of AI Programming Assistants: Successes and Challenges","created":"2023-03-30","cited_by_count":75},{"id":"2311.13240","title":"On the Calibration of Large Language Models and Alignment","created":"2023-11-22","cited_by_count":73},{"id":"2301.05809","title":"Who Should I Trust: AI or Myself? Leveraging Human and AI Correctness Likelihood to Promote Appropriate Trust in AI-Assisted Decision-Making","created":"2023-01-14","cited_by_count":67},{"id":"2005.00963","title":"On the Inference Calibration of Neural Machine Translation","created":"2020-05-03","cited_by_count":61},{"id":"2012.10988","title":"Post-hoc Uncertainty Calibration for Domain Drift Scenarios","created":"2020-12-20","cited_by_count":61},{"id":"2211.00151","title":"A Close Look into the Calibration of Pre-trained Language Models","created":"2022-10-31","cited_by_count":57},{"id":"2303.10845","title":"PanGu-{\\Sigma}: Towards Trillion Parameter Language Model with Sparse Heterogeneous Computing","created":"2023-03-20","cited_by_count":56},{"id":"2305.18607","title":"How Effective Are Neural Networks for Fixing Security Vulnerabilities","created":"2023-05-29","cited_by_count":52},{"id":"2312.15698","title":"RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair","created":"2023-12-25","cited_by_count":50},{"id":"2402.02047","title":"Calibration and Correctness of Language Models for Code","created":"2024-02-03","cited_by_count":49},{"id":"2207.06211","title":"Sample-dependent Adaptive Temperature Scaling for Improved Calibration","created":"2022-07-13","cited_by_count":48},{"id":"2308.11148","title":"LLaMA-Reviewer: Advancing Code Review Automation with Large Language Models through Parameter-Efficient Fine-Tuning","created":"2023-08-22","cited_by_count":47},{"id":"2404.04689","title":"Multicalibration for Confidence Scoring in LLMs","created":"2024-04-06","cited_by_count":46},{"id":"2309.08221","title":"Exploring the Potential of ChatGPT in Automated Code Refinement: An Empirical Study","created":"2023-09-15","cited_by_count":44},{"id":"2310.19208","title":"LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses","created":"2023-10-30","cited_by_count":44},{"id":"2404.02525","title":"Large Language Model for Vulnerability Detection and Repair: Literature Review and the Road Ahead","created":"2024-04-03","cited_by_count":42},{"id":"2206.02757","title":"Robust Calibration with Multi-domain Temperature Scaling","created":"2022-06-06","cited_by_count":39},{"id":"2403.08819","title":"Thermometer: Towards Universal Calibration for Large Language Models","created":"2024-02-20","cited_by_count":38},{"id":"2305.11248","title":"Investigating and Designing for Trust in AI-powered Code Generation Tools","created":"2023-05-18","cited_by_count":34},{"id":"2103.14540","title":"NL-EDIT: Correcting semantic parse errors through natural language interaction","created":"2021-03-26","cited_by_count":33},{"id":"2306.00074","title":"Human-Aligned Calibration for AI-Assisted Decision Making","created":"2023-05-31","cited_by_count":28},{"id":"2304.08653","title":"On Uncertainty Calibration and Selective Generation in Probabilistic Neural Summarization: A Benchmark Study","created":"2023-04-17","cited_by_count":25},{"id":"2302.07248","title":"Generation Probabilities Are Not Enough: Uncertainty Highlighting in AI Code Completions","created":"2023-02-14","cited_by_count":20},{"id":"2401.05136","title":"Code Review Automation: Strengths and Weaknesses of the State of the Art","created":"2024-01-10","cited_by_count":20},{"id":"2408.13597","title":"APPATCH: Automated Adaptive Prompting Large Language Models for Real-World Software Vulnerability Patching","created":"2024-08-24","cited_by_count":19},{"id":"2406.01806","title":"Contextualized Sequence Likelihood: Enhanced Confidence Scores for Natural Language Generation","created":"2024-06-03","cited_by_count":16},{"id":"2210.16494","title":"Aligning Offline Metrics and Human Judgments of Value for Code Generation Models","created":"2022-10-29","cited_by_count":14},{"id":"2406.13230","title":"Enhancing Language Model Factuality via Activation-Based Confidence Calibration and Guided Decoding","created":"2024-06-19","cited_by_count":14},{"id":"2404.19318","title":"Calibration of Large Language Models on Code Summarization","created":"2024-04-30","cited_by_count":12},{"id":"2411.13323","title":"Are Large Language Models Memorizing Bug Benchmarks?","created":"2024-11-20","cited_by_count":12},{"id":"2502.02757","title":"Too Noisy To Learn: Enhancing Data Quality for Code Review Comment Generation","created":"2025-02-04","cited_by_count":12},{"id":"2309.10852","title":"Using AI Uncertainty Quantification to Improve Human Decision-Making","created":"2023-09-19","cited_by_count":11},{"id":"2303.00732","title":"R-U-SURE? Uncertainty-Aware Code Suggestions By Maximizing Utility Across Random User Intents","created":"2023-03-01","cited_by_count":10},{"id":"2303.07221","title":"Generation-based Code Review Automation: How Far Are We?","created":"2023-03-13","cited_by_count":9},{"id":"2409.18952","title":"RepairBench: Leaderboard of Frontier Models for Program Repair","created":"2024-09-27","cited_by_count":9},{"id":"2402.13291","title":"DeepCode AI Fix: Fixing Security Vulnerabilities with Large Language Models","created":"2024-02-19","cited_by_count":7},{"id":"2307.13539","title":"Model Calibration in Dense Classification with Adaptive Label Perturbation","created":"2023-07-25","cited_by_count":3},{"id":"2409.04099","title":"What Guides Our Choices? Modeling Developers' Trust and Behavioral Intentions Towards GenAI","created":"2024-09-06","cited_by_count":3},{"id":"2502.08172","title":"Intention is All You Need: Refining Your Code from Your Intention","created":"2025-02-12","cited_by_count":3},{"id":"2504.10050","title":"Emotional Strain and Frustration in LLM Interactions in Software Engineering","created":"2025-04-14","cited_by_count":3}],"next_cursor":null}