Prior Beliefs Prejudice LLM-as-Judge: Evidence from Persuasion Evaluation (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models are increasingly used as judges to evaluate text quality, content and assess arguments. |
| Approach: | They propose to exploit belief-conditioned rating inflation by using persuasion-based probing to examine persuasive arguments. |
| Outcome: | The proposed model fails to evaluate persuasive arguments based on belief alignment . the model fails in three of the three tasks, with belief-conditioned rating inflation accounting for 88% of cases. |
Similar Papers
Can You Trick the Grader? Adversarial Persuasion of LLM Judges (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) are increasingly used as automated evaluators in practical settings . |
| Approach: | a study by the university of california reveals that persuasive language can bias large language models when scoring mathematical reasoning tasks. |
| Outcome: | The proposed model can bias judges when scoring mathematical reasoning tasks . Consistency causes the most severe distortion, with Consistencies leading to 8% distortion . |
What Evidence Do Language Models Find Convincing? (2024.acl-long)
Copied to clipboard
| Challenge: | Current retrieval-augmented language models are tasked with subjective, contentious, and conflicting queries. |
| Approach: | They construct a dataset that pairs controversial queries with real-world evidence documents . they find current models rely heavily on relevance of a website to the query . |
| Outcome: | The proposed dataset pairs controversial queries with real-world evidence documents that contain different facts, arguments, and answers. |
Can Language Models Recognize Convincing Arguments? (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies have found that large language models can generate persuasive content without engaging in human experimentation. |
| Approach: | They extend a dataset with debates, votes, and user traits to measure LLMs' ability to distinguish between strong and weak arguments, predict stances based on beliefs and demographic characteristics, and determine appeal of argument to individual based upon their traits. |
| Outcome: | The proposed tasks outperform human predictions in detecting convincing arguments in debates, votes, and user traits. |
Justice in Judgment: Unveiling (Hidden) Bias in LLM-assisted Peer Reviews (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing studies show that large language models carry implicit biases across race, gender, and religion . prior studies documented such biase based on text generation and classification tasks . |
| Approach: | They investigate bias in large language models by controlling metadata on author metadata . authors found affiliation bias favoring authors from highly ranked institutions . |
| Outcome: | The proposed model favors authors from highly ranked institutions, the authors show . the model also favors author affiliations from highly-ranked institutions . |
Reasons to Reject? Aligning Language Models with Judgments (2024.findings-acl)
Copied to clipboard
| Challenge: | a new framework for aligning large language models with judgments is proposed to help with alignment . a framework that allows for fine-grained inappropriate content detection and correction based on judgments . large language model alignment is critical for making artificial intelligence a reliable ally for humanity . |
| Approach: | They propose a framework that allows for fine-grained inappropriate content detection and correction based on judgments. |
| Outcome: | The proposed framework beats the 175B DaVinci003 and improves on AlpacaEval using judgments. |
It’s Not What You Say, It’s How You Say It: Evaluating LLM Responses to Expressions of Belief (2026.acl-long)
Copied to clipboard
| Challenge: | a typology is grounded in four linguistically motivated dimensions: form, evidentiality, epistemic stance, and tone. |
| Approach: | They propose a typology to evaluate how different EoBs affect whether models follow context versus prior knowledge. |
| Outcome: | The proposed model systematically evaluates 16 LLMs that differ in architecture, scale, and training stages . human listeners subconsciously interpret the belief based on how it is expressed, i.e., its explicitness, tone, or contextual cues. |
How Hypocritical Is Your LLM judge? Listener-Speaker Asymmetries in the Pragmatic Competence of Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are increasingly studied as repositories of linguistic knowledge. |
| Approach: | They compare LLMs’ performance as pragmatic listeners and as pragmatic speakers . they find a robust asymmetry between pragmatic evaluation and pragmatic generation . |
| Outcome: | The proposed models perform better as listeners than speakers, and produce more appropriate language than speakers. |
Think Again! The Effect of Test-Time Compute on Preferences, Opinions, and Beliefs of Large Language Models (2025.acl-industry)
Copied to clipboard
| Challenge: | Large Language Models exhibit subjective preferences, opinions, and beliefs, which may shape their behavior, influence advice and recommendations, and potentially reinforce certain viewpoints. |
| Approach: | They developed a benchmark to assess LLMs’ subjective inclinations across societal, cultural, ethical, and personal domains. |
| Outcome: | The proposed benchmark assesses LLMs’ subjective inclinations across societal, cultural, ethical, and personal domains. |
Humans or LLMs as the Judge? A Study on Judgement Bias (2024.emnlp-main)
Copied to clipboard
| Challenge: | Proprietary models such as GPT-4, Claude, Gemini-Pro and others are being democratized to improve evaluations of LLMs. |
| Approach: | They propose a framework that is free from referencing groundtruth annotations for investigating **Misinformation Oversight Bias**, **Gender Bia**,**Authority Bia* and **Beauty Bia's** on LLM and human judges. |
| Outcome: | The proposed framework investigates **Misinformation Oversight Bias**, **Gender Bia**,**Authority Bia* and **Beauty Bia' on LLM and human judges. |
Likelihood-based Mitigation of Evaluation Bias in Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are widely used to evaluate natural language generation tasks as automated metrics. |
| Approach: | They propose to use LLMs to evaluate sentences with higher likelihoods and lower likelihoods to mitigate the likelihood bias. |
| Outcome: | The proposed method overrates sentences with higher likelihoods while underrating sentences with lower likelihoods. |