Augmenting Human Evaluation with LLM Judges: How Many Human Reviews Do You Need?

• URL: http://arxiv.org/abs/2605.16354v1
• Date: Fri, 08 May 2026 17:13:08 GMT
• Title: Augmenting Human Evaluation with LLM Judges: How Many Human Reviews Do You Need?
• Abstract summary: Large language models (LLMs) are increasingly used as automated evaluators of AI systems, including in high-stakes applications.<n> Expert human ratings are costly and difficult to scale, whereas LLM ratings can be produced quickly at low cost.<n>This paper shifts the role of the LLM judge from substitutive to auxiliary, and formulates the LLM-as-a-judge paradigm as one of augmenting human evaluation.
• Score: 1.111977509278551
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) are increasingly used as automated evaluators of AI systems, including in high-stakes applications. In this role, LLMs are used to generate judgments about the quality, appropriateness, or even safety of model outputs. This approach is motivated by practical constraints. Expert human ratings are costly and difficult to scale, whereas LLM ratings can be produced quickly at low cost. However, current approaches to deploying LLM evaluators are ad hoc, typically limited to reporting agreement metrics between human and LLM judges as a justification for substitution of human ratings, and lack a formal basis for study design. This paper (1) shifts the role of the LLM judge from substitutive to auxiliary, and (2) formulates the LLM-as-a-judge paradigm as one of augmenting human evaluation through a two-stage sampling design, where LLM evaluations are measured for all observations at the first stage and human ratings are partially observed for a subsample at the second stage. We propose to use a doubly robust estimator from the missing data literature, which takes advantage of the robustness property against the prediction model, since the missingness model is known by design. Using the asymptotic variance of this estimator, we propose how sample sizes of human and LLM ratings can be determined to achieve a targeted level of power. We also show that a study can be efficiently designed by allocating more human ratings for types of evaluations where the predictability of LLM ratings is not high. To the best of our knowledge, there is very little guidance on how much human oversight should be retained when validating benchmarks.

Related papers

• On Evaluating LLM Alignment by Evaluating LLMs as Judges [68.15541137648721]
  evaluating large language models' (LLMs) alignment requires them to be helpful, honest, safe, and to precisely follow human instructions.<n>We examine the relationship between LLMs' generation and evaluation capabilities in aligning with human preferences.<n>We propose a benchmark that assesses alignment without directly evaluating model outputs.
  arXiv  Detail & Related papers  (2025-11-25T18:33:24Z)
• Can We Hide Machines in the Crowd? Quantifying Equivalence in LLM-in-the-loop Annotation Tasks [8.246529401043128]
  We aim to explore how labeling decisions -- by both humans and LLMs -- can be statistically evaluated across individuals.<n>We develop a statistical evaluation method based on Krippendorff's $alpha$, paired bootstrapping, and the Two One-Sided t-Tests (TOST) equivalence test procedure.<n>We apply this approach to two datasets -- MovieLens 100K and PolitiFact -- and find that the LLM is statistically indistinguishable from a human annotator in the former.
  arXiv  Detail & Related papers  (2025-10-08T05:17:33Z)
• Quantitative LLM Judges [60.773734899532336]
  We propose quantitative LLM judges, which align evaluation scores of existing LLM judges to humans in a given domain.<n>The models are trained to improve the score of the original judge using its rationale and score.<n>Our experiments show that quantitative judges can improve the predictive power of existing judges through post-hoc modeling.
  arXiv  Detail & Related papers  (2025-06-03T14:44:23Z)
• DnA-Eval: Enhancing Large Language Model Evaluation through Decomposition and Aggregation [75.81096662788254]
  Large Language Models (LLMs) are scalable and economical evaluators.<n>The question of how reliable these evaluators are has emerged as a crucial research question.<n>We propose Decompose and Aggregate, which breaks down the evaluation process into different stages based on pedagogical practices.
  arXiv  Detail & Related papers  (2024-05-24T08:12:30Z)
• Sample-Efficient Human Evaluation of Large Language Models via Maximum Discrepancy Competition [38.822535662755314]
  We propose a sample-efficient human evaluation method for large language models (LLMs)<n>Our method automatically and adaptively selects a compact set of input instructions that maximize semantic discrepancy between pairs of LLM responses.<n>Human evaluators then perform three-alternative forced choices on these paired responses, which are aggregated into a global ranking using Elo rating.
  arXiv  Detail & Related papers  (2024-04-10T01:26:24Z)
• An In-depth Evaluation of Large Language Models in Sentence Simplification with Error-based Human Assessment [9.156064716689833]
  This study provides in-depth insights into LLMs' performance while ensuring the reliability of the evaluation.<n>We select both closed-source and open-source LLMs, including GPT-4, Qwen2.5-72B, and Llama-3.2-3B.<n>Results show that LLMs generally generate fewer erroneous simplification outputs compared to the previous state-of-the-art.
  arXiv  Detail & Related papers  (2024-03-08T00:19:24Z)
• Exploring the Reliability of Large Language Models as Customized Evaluators for Diverse NLP Tasks [65.69651759036535]
  We analyze whether large language models (LLMs) can serve as reliable alternatives to humans.<n>This paper explores both conventional tasks (e.g., story generation) and alignment tasks (e.g., math reasoning)<n>We find that LLM evaluators can generate unnecessary criteria or omit crucial criteria, resulting in a slight deviation from the experts.
  arXiv  Detail & Related papers  (2023-10-30T17:04:35Z)
• Large Language Models are Not Yet Human-Level Evaluators for Abstractive Summarization [66.08074487429477]
  We investigate the stability and reliability of large language models (LLMs) as automatic evaluators for abstractive summarization. We find that while ChatGPT and GPT-4 outperform the commonly used automatic metrics, they are not ready as human replacements.
  arXiv  Detail & Related papers  (2023-05-22T14:58:13Z)
• Can Large Language Models Be an Alternative to Human Evaluations? [80.81532239566992]
  Large language models (LLMs) have demonstrated exceptional performance on unseen tasks when only the task instructions are provided. We show that the result of LLM evaluation is consistent with the results obtained by expert human evaluation.
  arXiv  Detail & Related papers  (2023-05-03T07:28:50Z)
• Benchmarking Large Language Models for News Summarization [79.37850439866938]
  Large language models (LLMs) have shown promise for automatic summarization but the reasons behind their successes are poorly understood. We find instruction tuning, and not model size, is the key to the LLM's zero-shot summarization capability.
  arXiv  Detail & Related papers  (2023-01-31T18:46:19Z)

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.