Challenge: Existing evaluation metrics for natural language generation tasks favor text generated by different LMs . human evaluation by experts is the most reliable approach, but it is costly and time-consuming .
Approach: They examine whether language model-driven evaluation metrics exhibit bias toward underlying language models in the context of summarization tasks.
Outcome: The proposed evaluation metrics tend to assign inflated scores to outputs generated by the very model they are based on.

Similar Papers

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.
BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation (2022.emnlp-main)

Copied to clipboard

Challenge: Currently, pre-trained language model (PLM) based metrics are widely adopted in text generation tasks.
Approach: They propose to use PLMs to encode stereotypical societal biases in PLM-based metrics . they show that popular metrics exhibit higher social bias than traditional metrics based on 6 attributes .
Outcome: The proposed method shows that PLM-based metrics exhibit higher social bias than traditional metrics on 6 attributes.
LLMs are Biased Evaluators But Not Biased for Fact-Centric Retrieval Augmented Generation (2025.findings-acl)

Copied to clipboard

Challenge: Recent studies have shown that large language models (LLMs) exhibit significant biases in evaluation tasks, especially in preferentially rating and favoring self-generated content.
Approach: They propose to simulate two critical phases of retrieval-augmented generation (RAG) frameworks where keyword extraction and factual accuracy take precedence over stylistic elements.
Outcome: The proposed model emulates two critical phases of the retrieval-augmented generation framework.
DHP Benchmark: Are LLMs Good NLG Evaluators? (2025.findings-naacl)

Copied to clipboard

Challenge: Large Language Models (LLMs) are increasingly serving as evaluators in Natural Language Generation (NLG) tasks.
Approach: They propose a framework that measures the discernment of Large Language Models (LLMs) across diverse NLG tasks.
Outcome: The proposed framework provides quantitative discernment scores for LLMs across four NLG tasks.
Leveraging Large Language Models for NLG Evaluation: Advances and Challenges (2024.emnlp-main)

Copied to clipboard

Challenge: introducing Large Language Models (LLMs) has opened new avenues for assessing generated content quality, e.g., coherence, creativity, and context relevance.
Approach: They propose a taxonomy for organizing existing LLM-based evaluation metrics and a structured framework to understand and compare them.
Outcome: The proposed taxonomy offers a framework to understand and compare LLM-based evaluation methods.
Are Large Language Model-based Evaluators the Solution to Scaling Up Multilingual Evaluation? (2024.findings-eacl)

Copied to clipboard

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.
LLMs for Generating and Evaluating Counterfactuals: A Comprehensive Study (2024.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) have shown remarkable performance in NLP tasks, but their efficacy in generating high-quality CFs remains uncertain.
Approach: They compare LLMs' ability to generate CFs that flip the original label and human CF's.
Outcome: The proposed models generate fluent CFs, but struggle to keep the induced changes minimal.
Co-Eval: Augmenting LLM-based Evaluation with Machine Metrics (2025.emnlp-main)

Copied to clipboard

Challenge: Existing LLMs suffer from biases and misalignment due to limited functional understanding and knowledge gaps.
Approach: They introduce a framework that leverages a criteria planner model and optimized machine metrics to enhance the scalability and fairness of LLM-based evaluation.
Outcome: The proposed framework reduces biases and improves alignment with human preferences, with gains of up to 0.324 in Spearman correlation.
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

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)

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations