MixEval: Deriving Wisdom of the Crowd from LLM Benchmark Mixtures

• URL: http://arxiv.org/abs/2406.06565v2
• Date: Sat, 12 Oct 2024 14:13:27 GMT
• Title: MixEval: Deriving Wisdom of the Crowd from LLM Benchmark Mixtures
• Authors: Jinjie Ni, Fuzhao Xue, Xiang Yue, Yuntian Deng, Mahir Shah, Kabir Jain, Graham Neubig, Yang You,
• Abstract summary: We propose MixEval, a new paradigm for establishing efficient, gold-standard evaluation by strategically mixing off-the-shelf benchmarks. It bridges (1) comprehensive and well-distributed real-world user queries and (2) efficient and fairly-graded ground-truth-based benchmarks, by matching queries mined from the web with similar queries from existing benchmarks.
• Score: 57.886592207948844
• License:
• Abstract: Evaluating large language models (LLMs) is challenging. Traditional ground-truth-based benchmarks fail to capture the comprehensiveness and nuance of real-world queries, while LLM-as-judge benchmarks suffer from grading biases and limited query quantity. Both of them may also become contaminated over time. User-facing evaluation, such as Chatbot Arena, provides reliable signals but is costly and slow. In this work, we propose MixEval, a new paradigm for establishing efficient, gold-standard LLM evaluation by strategically mixing off-the-shelf benchmarks. It bridges (1) comprehensive and well-distributed real-world user queries and (2) efficient and fairly-graded ground-truth-based benchmarks, by matching queries mined from the web with similar queries from existing benchmarks. Based on MixEval, we further build MixEval-Hard, which offers more room for model improvement. Our benchmarks' advantages lie in (1) a 0.96 model ranking correlation with Chatbot Arena arising from the highly impartial query distribution and grading mechanism, (2) fast, cheap, and reproducible execution (6% of the time and cost of MMLU), and (3) dynamic evaluation enabled by the rapid and stable data update pipeline. We provide extensive meta-evaluation and analysis for our and existing LLM benchmarks to deepen the community's understanding of LLM evaluation and guide future research directions.

Related papers

• Varco Arena: A Tournament Approach to Reference-Free Benchmarking Large Language Models [0.29687381456164]
  We propose a more flexible benchmarking approach for Large Language Models (LLMs) Our method, textittextbfVarco Arena, provides reference-free benchmarking of LLMs in tournament style. Our empirical results, supported by simulation experiments, demonstrate that the textittextbfVarco Arena tournament approach aligns better with the current Elo model for benchmarking LLMs.
  arXiv  Detail & Related papers  (2024-11-02T15:23:28Z)
• HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly [34.205934899868346]
  We present HELMET, a comprehensive benchmark encompassing seven diverse, application-centric categories. We find that synthetic tasks like NIAH are not good predictors of downstream performance. While most LCLMs achieve perfect NIAH scores, open-source models significantly lag behind closed ones when the task requires full-context reasoning.
  arXiv  Detail & Related papers  (2024-10-03T17:20:11Z)
• LiveBench: A Challenging, Contamination-Free LLM Benchmark [101.21578097087699]
  We release LiveBench, the first benchmark that contains frequently-updated questions from recent information sources. We evaluate many prominent closed-source models, as well as dozens of open-source models ranging from 0.5B to 110B in size. Questions will be added and updated on a monthly basis, and we will release new tasks and harder versions of tasks over time.
  arXiv  Detail & Related papers  (2024-06-27T16:47:42Z)
• Data Efficient Evaluation of Large Language Models and Text-to-Image Models via Adaptive Sampling [3.7467864495337624]
  SubLIME is a data-efficient evaluation framework for text-to-image models. Our approach ensures statistically aligned model rankings compared to full datasets. We leverage the HEIM leaderboard to cover 25 text-to-image models on 17 different benchmarks.
  arXiv  Detail & Related papers  (2024-06-21T07:38:55Z)
• Inference-Time Decontamination: Reusing Leaked Benchmarks for Large Language Model Evaluation [61.350306618479365]
  Leakage of benchmarks can prevent the accurate assessment of large language models' true performance. We propose Inference-Time Decontamination (ITD) to address this issue. ITD reduces inflated accuracy by 22.9% on GSM8K and 19.0% on MMLU.
  arXiv  Detail & Related papers  (2024-06-20T04:35:59Z)
• How to Prune Your Language Model: Recovering Accuracy on the "Sparsity May Cry'' Benchmark [60.72725673114168]
  We revisit the question of accurate BERT-pruning during fine-tuning on downstream datasets. We propose a set of general guidelines for successful pruning, even on the challenging SMC benchmark.
  arXiv  Detail & Related papers  (2023-12-21T03:11:30Z)
• Flames: Benchmarking Value Alignment of LLMs in Chinese [86.73527292670308]
  This paper proposes a value alignment benchmark named Flames. It encompasses both common harmlessness principles and a unique morality dimension that integrates specific Chinese values. Our findings indicate that all the evaluated LLMs demonstrate relatively poor performance on Flames.
  arXiv  Detail & Related papers  (2023-11-12T17:18:21Z)
• LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond [135.8013388183257]
  We propose a new protocol for inconsistency detection benchmark creation and implement it in a 10-domain benchmark called SummEdits. Most LLMs struggle on SummEdits, with performance close to random chance. The best-performing model, GPT-4, is still 8% below estimated human performance.
  arXiv  Detail & Related papers  (2023-05-23T21:50:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.