BUMP: A Benchmark of Unfaithful Minimal Pairs for Meta-Evaluation of Faithfulness Metrics (2023.acl-long)
Copied to clipboard
Liang Ma, Shuyang Cao, Robert L Logan IV, Di Lu, Shihao Ran, Ke Zhang, Joel Tetreault, Alejandro Jaimes
| Challenge: | Existing benchmarks measure the correlation with human judgements of faithfulness on model-generated summaries, but they are insufficient for diagnosing whether metrics are consistent, effective on human-written texts, and sensitive to different error types. |
| Approach: | They propose to use unfaithful minimal pairs to measure the consistency of automatic faithfulness metrics by comparing human-written summary pairs with a dataset of 889 human-writing, minimally different summary pairs. |
| Outcome: | The proposed benchmarks show that the most discriminative metrics tend not to be the most consistent, and that the best performing metrics are sensitive to errors. |
Similar Papers
FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization (2020.acl-main)
Copied to clipboard
| Challenge: | Existing automatic metrics do not capture errors in abstractive summarization models. |
| Approach: | They propose an automatic question answering metric for faithfulness that leverages recent advances in reading comprehension. |
| Outcome: | The proposed metric has significantly higher correlation with human faithfulness scores on highly abstracted summaries. |
Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics (2021.naacl-main)
Copied to clipboard
| Challenge: | Modern summarization models generate fluent but often factually unreliable outputs. |
| Approach: | They propose to use human annotations to identify different categories of factual errors and benchmark factuality metrics to improve summarization evaluation. |
| Outcome: | The proposed method identifies the proportion of different categories of factual errors and benchmarks their human judgements as well as their specific strengths and weaknesses. |
Extractive is not Faithful: An Investigation of Broad Unfaithfulness Problems in Extractive Summarization (2023.acl-long)
Copied to clipboard
| Challenge: | Abstractive summarization is less prone to unfaithfulness issues than abstractive summaries . but, unfaitfulness problems, i.e., hallucinating new information, are still a problem in extractive summarisation . |
| Approach: | They propose a typology with five types of broad unfaithfulness problems that can appear in extractive summaries, including and beyond not-entailment. |
| Outcome: | The proposed metric shows that it detects unfaithful summaries faster than existing faithfulness evaluation metrics. |
With a Little Push, NLI Models can Robustly and Efficiently Predict Faithfulness (2023.acl-short)
Copied to clipboard
| Challenge: | Conditional language models generate unfaithful output that is not supported by their input . this jeopardizes trust in real-world applications, raising a need for automatic faithfulness metrics. |
| Approach: | They propose to augment conditional language models with robust inference procedures to improve faithfulness. |
| Outcome: | The proposed approach outperforms existing models on the TRUE benchmark. |
USB: A Unified Summarization Benchmark Across Tasks and Domains (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing summarization benchmarks lack the rich annotations needed to address important problems related to control and reliability. |
| Approach: | They propose a Wikipedia-derived summarization benchmark with crowd-sourced annotations . they find that fine-tuned models outperform larger few-shot prompted language models . |
| Outcome: | The proposed model outperforms many-shot prompted language models on multiple tasks . the proposed model is based on Wikipedia annotations and can be used in other domains . |
On Faithfulness and Factuality in Abstractive Summarization (2020.acl-main)
Copied to clipboard
| Challenge: | Existing conditional text generation models produce unfaithful and unfaithed summaries . current models accomplish a high level of fluency and coherence . |
| Approach: | They propose to use pretrained models for document summarization to better understand hallucinations . they find that textual entailment measures better correlate with faithfulness . |
| Outcome: | The proposed models generate faithful and factual summaries as evaluated by humans. |
Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error Detectors (2023.acl-long)
Copied to clipboard
Liyan Tang, Tanya Goyal, Alex Fabbri, Philippe Laban, Jiacheng Xu, Semih Yavuz, Wojciech Kryscinski, Justin Rousseau, Greg Durrett
| Challenge: | Abstractive summarization systems still include factual errors in generated summaries despite recent improvements in factuality detection . |
| Approach: | They aggregate factuality error annotations from nine existing datasets and stratify them according to the underlying summarization model. |
| Outcome: | The proposed method improves on the ChatGPT-based model and shows that it is not superior for all error types. |
Verify with Caution: The Pitfalls of Relying on Imperfect Factuality Metrics (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in large language models have led to optimism that they can serve as reliable evaluators of natural language outputs. |
| Approach: | They propose to use factuality metrics to evaluate natural language outputs . they find they misestimate the factual accuracy of NLG systems . |
| Outcome: | The proposed metrics are inconsistent with each other and often misestimate the factual accuracy of NLG systems, causing biases against paraphrased outputs and outputs that draw upon faraway parts of the source documents. |
Multi-View Source Ablation for Faithful Summarization (2023.findings-eacl)
Copied to clipboard
| Challenge: | MuFaSSa is a metric for evaluating faithfulness of abstractive summaries . it uses different strategies to remove information from source document to form multiple ablated views . |
| Approach: | They propose a metric for evaluating faithfulness of abstractive summaries using multiple ablated views. |
| Outcome: | The proposed metric outperforms existing models on summarization tasks and human-annotated faithfulness labels. |
SummEval: Re-evaluating Summarization Evaluation (2021.tacl-1)
Copied to clipboard
Alexander R. Fabbri, Wojciech Kryściński, Bryan McCann, Caiming Xiong, Richard Socher, Dragomir Radev
| Challenge: | a lack of comprehensive studies on evaluation metrics for text summarization hinders progress . a new study aims to improve evaluation metrics that correlate with human judgments . |
| Approach: | They propose to re-evaluate automatic evaluation metrics and share a toolkit for evaluation . they hope to promote a more complete evaluation protocol for text summarization . |
| Outcome: | The proposed evaluation metrics are inconsistent with existing evaluation protocols. |