English
Related papers

Related papers: TRUE: Re-evaluating Factual Consistency Evaluation

200 papers

While modern visual generation models excel at creating aesthetically pleasing natural images, they struggle with producing or editing structured visuals like charts, diagrams, and mathematical figures, which demand composition planning,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Le Zhuo , Songhao Han , Yuandong Pu , Boxiang Qiu , Sayak Paul , Yue Liao , Yihao Liu , Jie Shao , Xi Chen , Si Liu , Hongsheng Li

Traditional metrics like BLEU and BERTScore fail to capture semantic fidelity in generative text-to-text tasks. We adapt the Cross-Examination Framework (CEF) for a reference-free, multi-dimensional evaluation by treating the source and…

Computation and Language · Computer Science 2026-01-28 Tathagata Raha , Clement Christophe , Nada Saadi , Hamza A Javed , Marco AF Pimentel , Ronnie Rajan , Praveenkumar Kanithi

Validating evaluation metrics for NLG typically relies on expensive and time-consuming human annotations, which predominantly exist only for English datasets. We propose \textit{LLM as a Meta-Judge}, a scalable framework that utilizes LLMs…

Computation and Language · Computer Science 2026-03-11 Lukáš Eigler , Jindřich Libovický , David Hurych

Large Language Models (LLMs) changed the way we design and interact with software systems. Their ability to process and extract information from text has drastically improved productivity in a number of routine tasks. Developers that want…

Machine Learning · Computer Science 2025-08-26 Federico Errica , Giuseppe Siracusano , Davide Sanvito , Roberto Bifulco

Following how humans communicate, free-text rationales aim to use natural language to explain neural language model (LM) behavior. However, free-text rationales' unconstrained nature makes them prone to hallucination, so it is important to…

Computation and Language · Computer Science 2022-12-21 Aaron Chan , Shaoliang Nie , Liang Tan , Xiaochang Peng , Hamed Firooz , Maziar Sanjabi , Xiang Ren

Large language models (LLMs), especially when instruction-tuned for chat, have become part of our daily lives, freeing people from the process of searching, extracting, and integrating information from multiple sources by offering a…

Computation and Language · Computer Science 2024-11-01 Yuxia Wang , Minghan Wang , Muhammad Arslan Manzoor , Fei Liu , Georgi Georgiev , Rocktim Jyoti Das , Preslav Nakov

Large Language Models (LLMs) have shown impressive capability in language generation and understanding, but their tendency to hallucinate and produce factually incorrect information remains a key limitation. To verify LLM-generated contents…

Computation and Language · Computer Science 2025-06-03 Kushan Mitra , Dan Zhang , Sajjadur Rahman , Estevam Hruschka

Evaluating consistency in large language models (LLMs) is crucial for ensuring reliability, particularly in complex, multi-step interactions between humans and LLMs. Traditional self-consistency methods often miss subtle semantic changes in…

Artificial Intelligence · Computer Science 2025-06-18 Zhaochen Hong , Haofei Yu , Jiaxuan You

Hallucinations pose a challenge to the application of large language models (LLMs) thereby motivating the development of metrics to evaluate factual precision. We observe that popular metrics using the Decompose-Then-Verify framework, such…

Computation and Language · Computer Science 2024-10-17 Zhengping Jiang , Jingyu Zhang , Nathaniel Weir , Seth Ebner , Miriam Wanner , Kate Sanders , Daniel Khashabi , Anqi Liu , Benjamin Van Durme

Single document news summarization has seen substantial progress on faithfulness in recent years, driven by research on the evaluation of factual consistency, or hallucinations. We ask whether these advances carry over to other text…

Computational methods to aid journalists in the task often require adapting a model to specific domains and generating explanations. However, most automated fact-checking methods rely on three-class datasets, which do not accurately reflect…

Computation and Language · Computer Science 2024-10-08 Jing Yang , Anderson Rocha

The Shared Task on Evaluating Accuracy focused on techniques (both manual and automatic) for evaluating the factual accuracy of texts produced by neural NLG systems, in a sports-reporting domain. Four teams submitted evaluation techniques…

Computation and Language · Computer Science 2021-08-17 Craig Thomson , Ehud Reiter

Counterfactual text generation aims to minimally change a text, such that it is classified differently. Judging advancements in method development for counterfactual text generation is hindered by a non-uniform usage of data sets and…

Computation and Language · Computer Science 2024-08-14 Van Bach Nguyen , Jörg Schlötterer , Christin Seifert

Evaluating automatically generated text is generally hard due to the inherently subjective nature of many aspects of the output quality. This difficulty is compounded in automatic consultation note generation by differing opinions between…

Computation and Language · Computer Science 2022-11-18 Aleksandar Savkov , Francesco Moramarco , Alex Papadopoulos Korfiatis , Mark Perera , Anya Belz , Ehud Reiter

Hallucinated outputs from large language models (LLMs) pose risks in the medical domain, especially for lay audiences making health-related decisions. Existing automatic factual consistency evaluation methods, such as entailment- and…

Computation and Language · Computer Science 2026-03-20 Zhiwen You , Yue Guo

Neural models for response generation produce responses that are semantically plausible but not necessarily factually consistent with facts describing the speaker's persona. These models are trained with fully supervised learning where the…

Computation and Language · Computer Science 2021-02-16 Mohsen Mesgar , Edwin Simpson , Iryna Gurevych

The increased use of large language models (LLMs) across a variety of real-world applications calls for mechanisms to verify the factual accuracy of their outputs. Difficulties lie in assessing the factuality of free-form responses in open…

Computation and Language · Computer Science 2025-10-30 Yuxia Wang , Minghan Wang , Hasan Iqbal , Georgi Georgiev , Jiahui Geng , Preslav Nakov

Evaluating text-to-image generative models remains a challenge, despite the remarkable progress being made in their overall performances. While existing metrics like CLIPScore work for coarse evaluations, they lack the sensitivity to…

Computer Vision and Pattern Recognition · Computer Science 2024-11-06 Georgia Gabriela Sampaio , Ruixiang Zhang , Shuangfei Zhai , Jiatao Gu , Josh Susskind , Navdeep Jaitly , Yizhe Zhang

While recent years have witnessed the emergence of various explainable methods in machine learning, to what degree the explanations really represent the reasoning process behind the model prediction -- namely, the faithfulness of…

Computation and Language · Computer Science 2021-09-07 Yingqiang Ge , Shuchang Liu , Zelong Li , Shuyuan Xu , Shijie Geng , Yunqi Li , Juntao Tan , Fei Sun , Yongfeng Zhang

Work on instruction-tuned Large Language Models (LLMs) has used automatic methods based on text overlap and LLM judgments as cost-effective alternatives to human evaluation. In this paper, we perform a meta-evaluation of such methods and…

Computation and Language · Computer Science 2024-10-03 Ehsan Doostmohammadi , Oskar Holmström , Marco Kuhlmann