Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMs

• URL: http://arxiv.org/abs/2509.01790v1
• Date: Mon, 01 Sep 2025 21:38:28 GMT
• Title: Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMs
• Authors: Andong Hua, Kenan Tang, Chenhe Gu, Jindong Gu, Eric Wong, Yao Qin,
• Abstract summary: High prompt sensitivity has been widely accepted as a core limitation of large language models.<n>This work asks: Is the widely reported high prompt sensitivity truly an inherent weakness of LLMs, or is it largely an artifact of evaluation processes?<n>We find that much of the prompt sensitivity stems from evaluation methods, including log-likelihood scoring and rigid answer matching.
• Score: 34.51801559719707
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Prompt sensitivity, referring to the phenomenon where paraphrasing (i.e., repeating something written or spoken using different words) leads to significant changes in large language model (LLM) performance, has been widely accepted as a core limitation of LLMs. In this work, we revisit this issue and ask: Is the widely reported high prompt sensitivity truly an inherent weakness of LLMs, or is it largely an artifact of evaluation processes? To answer this question, we systematically evaluate 7 LLMs (e.g., GPT and Gemini family) across 6 benchmarks, including both multiple-choice and open-ended tasks on 12 diverse prompt templates. We find that much of the prompt sensitivity stems from heuristic evaluation methods, including log-likelihood scoring and rigid answer matching, which often overlook semantically correct responses expressed through alternative phrasings, such as synonyms or paraphrases. When we adopt LLM-as-a-Judge evaluations, we observe a substantial reduction in performance variance and a consistently higher correlation in model rankings across prompts. Our findings suggest that modern LLMs are more robust to prompt templates than previously believed, and that prompt sensitivity may be more an artifact of evaluation than a flaw in the models.

Related papers

• Evaluating & Reducing Deceptive Dialogue From Language Models with Multi-turn RL [64.3268313484078]
  Large Language Models (LLMs) interact with millions of people worldwide in applications such as customer support, education and healthcare.<n>Their ability to produce deceptive outputs, whether intentionally or inadvertently, poses significant safety concerns.<n>We investigate the extent to which LLMs engage in deception within dialogue, and propose the belief misalignment metric to quantify deception.
  arXiv  Detail & Related papers  (2025-10-16T05:29:36Z)
• Can Reasoning Help Large Language Models Capture Human Annotator Disagreement? [84.32752330104775]
  Variation in human annotation (i.e., disagreements) is common in NLP.<n>We evaluate the influence of different reasoning settings on Large Language Model disagreement modeling.<n>Surprisingly, our results show that RLVR-style reasoning degrades performance in disagreement modeling.
  arXiv  Detail & Related papers  (2025-06-24T09:49:26Z)
• Order Matters in Hallucination: Reasoning Order as Benchmark and Reflexive Prompting for Large-Language-Models [0.0]
  Large language models (LLMs) have generated significant attention since their inception, finding applications across various academic and industrial domains.<n>LLMs often suffer from the "hallucination problem", where outputs, though grammatically and logically coherent, lack factual accuracy or are entirely fabricated.
  arXiv  Detail & Related papers  (2024-08-09T14:34:32Z)
• Social Bias Evaluation for Large Language Models Requires Prompt Variations [38.91306092184724]
  Large Language Models (LLMs) exhibit considerable social biases. This paper investigates the sensitivity of LLMs when changing prompt variations. We show that LLMs have tradeoffs between performance and social bias caused by the prompts.
  arXiv  Detail & Related papers  (2024-07-03T14:12:04Z)
• Analyzing LLM Behavior in Dialogue Summarization: Unveiling Circumstantial Hallucination Trends [38.86240794422485]
  We evaluate the faithfulness of large language models for dialogue summarization. Our evaluation reveals subtleties as to what constitutes a hallucination. We introduce two prompt-based approaches for fine-grained error detection that outperform existing metrics.
  arXiv  Detail & Related papers  (2024-06-05T17:49:47Z)
• RankPrompt: Step-by-Step Comparisons Make Language Models Better Reasoners [38.30539869264287]
  Large Language Models (LLMs) have achieved impressive performance across various reasoning tasks. However, even state-of-the-art LLMs such as ChatGPT are prone to logical errors during their reasoning processes. We introduce RankPrompt, a new prompting method that enables LLMs to self-rank their responses without additional resources.
  arXiv  Detail & Related papers  (2024-03-19T02:34:18Z)
• Fact-and-Reflection (FaR) Improves Confidence Calibration of Large Language Models [84.94220787791389]
  We propose Fact-and-Reflection (FaR) prompting, which improves the LLM calibration in two steps. Experiments show that FaR achieves significantly better calibration; it lowers the Expected Error by 23.5%. FaR even elicits the capability of verbally expressing concerns in less confident scenarios.
  arXiv  Detail & Related papers  (2024-02-27T01:37:23Z)
• InfiMM-Eval: Complex Open-Ended Reasoning Evaluation For Multi-Modal Large Language Models [50.03163753638256]
  Multi-modal Large Language Models (MLLMs) are increasingly prominent in the field of artificial intelligence. Our benchmark comprises three key reasoning categories: deductive, abductive, and analogical reasoning. We evaluate a selection of representative MLLMs using this rigorously developed open-ended multi-step elaborate reasoning benchmark.
  arXiv  Detail & Related papers  (2023-11-20T07:06:31Z)
• 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)
• Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves [57.974103113675795]
  We present a method named Rephrase and Respond' (RaR) which allows Large Language Models to rephrase and expand questions posed by humans. RaR serves as a simple yet effective prompting method for improving performance. We show that RaR is complementary to the popular Chain-of-Thought (CoT) methods, both theoretically and empirically.
  arXiv  Detail & Related papers  (2023-11-07T18:43:34Z)
• ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks [91.55895047448249]
  This paper presents ReEval, an LLM-based framework using prompt chaining to perturb the original evidence for generating new test cases. We implement ReEval using ChatGPT and evaluate the resulting variants of two popular open-domain QA datasets. Our generated data is human-readable and useful to trigger hallucination in large language models.
  arXiv  Detail & Related papers  (2023-10-19T06:37:32Z)
• Are Large Language Models Really Robust to Word-Level Perturbations? [68.60618778027694]
  We propose a novel rational evaluation approach that leverages pre-trained reward models as diagnostic tools. Longer conversations manifest the comprehensive grasp of language models in terms of their proficiency in understanding questions. Our results demonstrate that LLMs frequently exhibit vulnerability to word-level perturbations that are commonplace in daily language usage.
  arXiv  Detail & Related papers  (2023-09-20T09:23:46Z)
• Semantic Consistency for Assuring Reliability of Large Language Models [9.040736633675136]
  Large Language Models (LLMs) exhibit remarkable fluency and competence across various natural language tasks.<n>We introduce a general measure of semantic consistency, and formulate multiple versions of this metric to evaluate the performance of various LLMs.<n>We propose a novel prompting strategy, called Ask-to-Choose (A2C), to enhance semantic consistency.
  arXiv  Detail & Related papers  (2023-08-17T18:11:33Z)

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.