{"list":"other","total":53,"rows":[{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"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":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"2305.01210","title":"Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation","created":"2023-05-02","cited_by_count":1391},{"id":"1910.12840","title":"Evaluating the Factual Consistency of Abstractive Text Summarization","created":"2019-10-28","cited_by_count":584},{"id":"2401.00595","title":"State of What Art? A Call for Multi-Prompt LLM Evaluation","created":"2023-12-31","cited_by_count":310},{"id":"2402.14992","title":"tinyBenchmarks: evaluating LLMs with fewer examples","created":"2024-02-22","cited_by_count":310},{"id":"2412.06559","title":"ProcessBench: Identifying Process Errors in Mathematical Reasoning","created":"2024-12-09","cited_by_count":292},{"id":"2308.11483","title":"Large Language Models Sensitivity to The Order of Options in Multiple-Choice Questions","created":"2023-08-22","cited_by_count":263},{"id":"2406.04770","title":"WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild","created":"2024-06-07","cited_by_count":218},{"id":"2405.14782","title":"Lessons from the Trenches on Reproducible Evaluation of Language Models","created":"2024-05-23","cited_by_count":179},{"id":"2410.12405","title":"ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs","created":"2024-10-16","cited_by_count":149},{"id":"2106.09647","title":"Deep Learning Through the Lens of Example Difficulty","created":"2021-06-17","cited_by_count":141},{"id":"2405.10938","title":"Observational Scaling Laws and the Predictability of Language Model Performance","created":"2024-05-17","cited_by_count":130},{"id":"2210.06726","title":"Explanations from Large Language Models Make Small Reasoners Better","created":"2022-10-13","cited_by_count":124},{"id":"2505.08638","title":"TRAIL: Trace Reasoning and Agentic Issue Localization","created":"2025-05-13","cited_by_count":104},{"id":"2406.12334","title":"What Did I Do Wrong? Quantifying LLMs' Sensitivity and Consistency to Prompt Engineering","created":"2024-06-18","cited_by_count":90},{"id":"2307.16648","title":"LLMs4OL: Large Language Models for Ontology Learning","created":"2023-07-31","cited_by_count":77},{"id":"2305.14483","title":"Language Model Self-improvement by Reinforcement Learning Contemplation","created":"2023-05-23","cited_by_count":75},{"id":"2306.00946","title":"Exposing Attention Glitches with Flip-Flop Language Modeling","created":"2023-06-01","cited_by_count":75},{"id":"2405.17202","title":"Efficient multi-prompt evaluation of LLMs","created":"2024-05-27","cited_by_count":73},{"id":"2308.11696","title":"Efficient Benchmarking of Language Models","created":"2023-08-22","cited_by_count":71},{"id":"2306.09841","title":"Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond","created":"2023-06-16","cited_by_count":65},{"id":"1905.10854","title":"Let's Agree to Agree: Neural Networks Share Classification Order on Real Datasets","created":"2019-05-26","cited_by_count":56},{"id":"2407.06153","title":"What's Wrong with Your Code Generated by Large Language Models? An Extensive Study","created":"2024-07-08","cited_by_count":53},{"id":"2404.03602","title":"Evaluating LLMs at Detecting Errors in LLM Responses","created":"2024-04-04","cited_by_count":50},{"id":"2406.00755","title":"Evaluating Mathematical Reasoning of Large Language Models: A Focus on Error Identification and Correction","created":"2024-06-02","cited_by_count":45},{"id":"2109.06096","title":"The Grammar-Learning Trajectories of Neural Language Models","created":"2021-09-13","cited_by_count":36},{"id":"2309.13063","title":"Using Large Language Models to Generate, Validate, and Apply User Intent Taxonomies","created":"2023-09-14","cited_by_count":34},{"id":"2404.16966","title":"Examining the robustness of LLM evaluation to the distributional assumptions of benchmarks","created":"2024-04-25","cited_by_count":31},{"id":"2503.06378","title":"General Scales Unlock AI Evaluation with Explanatory and Predictive Power","created":"2025-03-09","cited_by_count":31},{"id":"2406.08731","title":"Towards Understanding the Characteristics of Code Generation Errors Made by Large Language Models","created":"2024-06-13","cited_by_count":30},{"id":"2503.08893","title":"EvalTree: Profiling Language Model Weaknesses via Hierarchical Capability Trees","created":"2025-03-11","cited_by_count":27},{"id":"2403.12173","title":"TnT-LLM: Text Mining at Scale with Large Language Models","created":"2024-03-18","cited_by_count":26},{"id":"2407.17468","title":"WildHallucinations: Evaluating Long-form Factuality in LLMs with Real-World Entity Queries","created":"2024-07-24","cited_by_count":26},{"id":"2406.03487","title":"Analyzing LLM Behavior in Dialogue Summarization: Unveiling Circumstantial Hallucination Trends","created":"2024-06-05","cited_by_count":25},{"id":"2412.06540","title":"Sloth: scaling laws for LLM skills to predict multi-benchmark performance across families","created":"2024-12-09","cited_by_count":24},{"id":"2309.09898","title":"Towards Ontology Construction with Language Models","created":"2023-09-18","cited_by_count":23},{"id":"2502.02362","title":"Premise-Augmented Reasoning Chains Improve Error Identification in Math reasoning with LLMs","created":"2025-02-04","cited_by_count":22},{"id":"2503.01622","title":"DOVE: A Large-Scale Multi-Dimensional Predictions Dataset Towards Meaningful LLM Evaluation","created":"2025-03-03","cited_by_count":21},{"id":"2503.17439","title":"LEMMA: Learning from Errors for MatheMatical Advancement in LLMs","created":"2025-03-21","cited_by_count":21},{"id":"1909.06814","title":"Automatically Extracting Challenge Sets for Non local Phenomena in Neural Machine Translation","created":"2019-09-15","cited_by_count":15},{"id":"2505.08827","title":"RLSR: Reinforcement Learning from Self Reward","created":"2025-05-12","cited_by_count":14},{"id":"2505.22169","title":"ReliableEval: A Recipe for Stochastic LLM Evaluation via Method of Moments","created":"2025-05-28","cited_by_count":11},{"id":"2502.19412","title":"The Mighty ToRR: A Benchmark for Table Reasoning and Robustness","created":"2025-02-26","cited_by_count":10},{"id":"2507.20208","title":"From Benchmarks to Skills: Low-Rank Factors for LLM Evaluation","created":"2025-07-27","cited_by_count":9},{"id":"2508.09662","title":"EffiEval: Efficient and Generalizable Model Evaluation via Capability Coverage Maximization","created":"2025-08-13","cited_by_count":9},{"id":"2310.00160","title":"Self-Specialization: Uncovering Latent Expertise within Large Language Models","created":"2023-09-29","cited_by_count":5},{"id":"2506.02204","title":"BehaviorBox: Automated Discovery of Fine-Grained Performance Differences Between Language Models","created":"2025-06-02","cited_by_count":5},{"id":"2411.01539","title":"LLMs and the Madness of Crowds","created":"2024-11-03","cited_by_count":2},{"id":"2410.17051","title":"Data-driven Coreference-based Ontology Building","created":"2024-10-22","cited_by_count":1}],"next_cursor":null}