Peiyi Wang, Lei Li, Liang Chen, Zefan Cai, Dawei Zhu, Binghuai Lin, Yunbo Cao, Lingpeng Kong, Qi Liu, Tianyu Liu, Zhifang Sui
| Challenge: | Existing evaluation frameworks that use large language models as referees are insufficient for accurately assessing their alignment with human intent. |
| Approach: | They propose a calibration framework to address positional bias in large language models as evaluators by manually annotating the “win/tie/lose” outcomes of responses from ChatGPT and Vicuna-13B in the Vicun A Benchmark’s question prompt. |
| Outcome: | The proposed framework alleviates evaluation bias, resulting in closer alignment with human judgments. |
Similar Papers
An Empirical Analysis on Large Language Models in Debate Evaluation (2024.acl-short)
Copied to clipboard
| Challenge: | Prior research in automatic debate evaluation relied on pre-trained encoders and the modeling of argument relations and structures. |
| Approach: | They investigate the capabilities and inherent biases of advanced large language models (LLMs) such as GPT-3.5 and GPT-4 in the context of debate evaluation. |
| Outcome: | The proposed models outperform state-of-the-art methods on extensive datasets and show that they are more accurate than previous models. |
Are Large Language Model-based Evaluators the Solution to Scaling Up Multilingual Evaluation? (2024.findings-eacl)
Copied to clipboard
Rishav Hada, Varun Gumma, Adrian Wynter, Harshita Diddee, Mohamed Ahmed, Monojit Choudhury, Kalika Bali, Sunayana Sitaram
| Challenge: | Large Language Models (LLMs) excel in various tasks, but their evaluation, especially in languages beyond the top 20, remains inadequate due to existing benchmarks and metrics limitations. |
| Approach: | They propose to use Large Language Models as evaluators to rank or score other models’ outputs by calibrating them against 20K human judgments across three text-generation tasks, five metrics, and eight languages. |
| Outcome: | The proposed evaluation methods can be used to improve multilingual evaluation by calibrating them against 20K human judgments across three text-generation tasks, five metrics, and eight languages. |
Evaluation Metrics in the Era of GPT-4: Reliably Evaluating Large Language Models on Sequence to Sequence Tasks (2023.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) evaluation is a patchy and inconsistent landscape . established automatic evaluation metrics are poor surrogates, correlating weakly with human judgement. |
| Approach: | They propose to use both automatic and human evaluation to evaluate generative LLMs on three NLP benchmarks: text summarisation, text simplification and grammatical error correction. |
| Outcome: | The proposed model outperforms many popular models according to human reviewers on the majority of metrics, while scoring much worse when using classic automatic evaluation metrics. |
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. |
Characterizing Positional Bias in Large Language Models: A Multi-Model Evaluation of Prompt Order Effects (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models can be influenced by various forms of biases, says a new study . positional bias affects how LLMs interpret and weigh information, the authors say . |
| Approach: | a new study examines the impact of positional bias on large language models . positional biased models prioritize items based on their position rather than content or quality . |
| Outcome: | a new study shows that LLMs prioritize items based on their position rather than content or quality . the positional bias affects how LLM interpret and weigh information, the authors say . |
Large Language Models are Not Yet Human-Level Evaluators for Abstractive Summarization (2023.findings-emnlp)
Copied to clipboard
| Challenge: | ChatGPT and GPT-4 are popular as evaluation metric for complex generative tasks . however, they are not ready as human replacements due to significant limitations . |
| Approach: | They conduct extensive analysis to examine the stability and reliability of LLMs as automatic evaluators for abstractive summarization. |
| Outcome: | The proposed methods outperform the commonly used automatic metrics but are not ready for human evaluation due to significant limitations. |
LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs (2025.naacl-long)
Copied to clipboard
Do Xuan Long, Ngoc-Hai Nguyen, Tiviatis Sim, Hieu Dao, Shafiq Joty, Kenji Kawaguchi, Nancy F. Chen, Min-Yen Kan
| Challenge: | Using format-following capabilities, state-of-the-art large language models (LLMs) can be leveraged to tailor outputs to specific task formats. |
| Approach: | They propose to define a format bias evaluation metric and establish effective strategies to reduce it. |
| Outcome: | The proposed evaluation reduces the variance in ChatGPT’s performance among wrapping formats from 235.33 to 0.71 (%2) |
Style Over Substance: Evaluation Biases for Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Ranking the relative performance of large language models based on Elo ratings is gaining popularity . however, the extent to which humans and LLMs are capable evaluators remains uncertain . |
| Approach: | They propose to evaluate machine-generated text across multiple dimensions using the Elo rating system . they propose to use crowd-sourced and expert annotators to rank models based on Elo ratings . |
| Outcome: | The proposed method improves the quality of LLM-based evaluations, but there is no improvement in crowd-sourced evaluations. |
Large Language Model as an Assignment Evaluator: Insights, Feedback, and Challenges in a 1000+ Student Course (2024.emnlp-main)
Copied to clipboard
| Challenge: | Using large language models (LLMs) for automatic evaluation has become an important evaluation method in NLP research. |
| Approach: | They use large language models (LLMs) for automatic evaluation to evaluate a sample . they propose several recommendations for integrating LLMs into future classroom evaluations . |
| Outcome: | The proposed model is able to output high scores without meeting the evaluation instructions, the authors note . their model is not able for students to manipulate the model to output specific strings, they say . |
Benchmarking Cognitive Biases in Large Language Models as Evaluators (2024.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have been shown to be effective as automatic evaluators with simple prompting and in-context learning. |
| Approach: | They assemble 16 Large Language Models and evaluate their outputs by preference ranking . they introduce a cognitive bias benchmark to measure six different cognitive biases in LLM evaluation outputs. |
| Outcome: | The proposed model is biased on the CoBBLer benchmark, indicating that machine preferences are misaligned with humans. |