English
Related papers

Related papers: ACUTE-EVAL: Improved Dialogue Evaluation with Opti…

200 papers

As AI becomes more integral in our lives, the need for transparency and responsibility grows. While natural language explanations (NLEs) are vital for clarifying the reasoning behind AI decisions, evaluating them through human judgments is…

Computation and Language · Computer Science 2024-03-27 Fan Huang , Haewoon Kwak , Kunwoo Park , Jisun An

Evaluation of large language model (LLM) outputs requires users to make critical judgments about the best outputs across various configurations. This process is costly and takes time given the large amounts of data. LLMs are increasingly…

Chatbots are designed to carry out human-like conversations across different domains, such as general chit-chat, knowledge exchange, and persona-grounded conversations. To measure the quality of such conversational agents, a dialogue…

Computation and Language · Computer Science 2022-01-19 Chen Zhang , Luis Fernando D'Haro , Thomas Friedrichs , Haizhou Li

This paper introduces a novel Self-supervised Fine-grained Dialogue Evaluation framework (SelF-Eval). The core idea is to model the correlation between turn quality and the entire dialogue quality. We first propose a novel automatic data…

Computation and Language · Computer Science 2022-09-19 Longxuan Ma , Ziyu Zhuang , Weinan Zhang , Mingda Li , Ting Liu

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

In spoken dialogue systems, we aim to deploy artificial intelligence to build automated dialogue agents that can converse with humans. Dialogue systems are increasingly being designed to move beyond just imitating conversation and also…

Computation and Language · Computer Science 2021-11-03 Atharv Singh Patlan , Shiven Tripathi , Shubham Korde

Prior research has shown that typical fact-checking models for stand-alone claims struggle with claims made in dialogues. As a solution, fine-tuning these models on labelled dialogue data has been proposed. However, creating separate models…

Computation and Language · Computer Science 2023-11-15 Eric Chamoun , Marzieh Saeidi , Andreas Vlachos

Collecting human judgements is currently the most reliable evaluation method for natural language generation systems. Automatic metrics have reported flaws when applied to measure quality aspects of generated text and have been shown to…

Computation and Language · Computer Science 2022-04-29 Thórhildur Thorleiksdóttir , Cedric Renggli , Nora Hollenstein , Ce Zhang

Automatic evaluation of language generation systems is a well-studied problem in Natural Language Processing. While novel metrics are proposed every year, a few popular metrics remain as the de facto metrics to evaluate tasks such as image…

Computation and Language · Computer Science 2020-10-27 Ozan Caglayan , Pranava Madhyastha , Lucia Specia

Automatically evaluating text-based, non-task-oriented dialogue systems (i.e., `chatbots') remains an open problem. Previous approaches have suffered challenges ranging from poor correlation with human judgment to poor generalization and…

Computation and Language · Computer Science 2021-04-14 Ian Berlot-Attwell , Frank Rudzicz

Automated generalisation has known important improvements these last few years. However, an issue that still deserves more study concerns the automatic evaluation of generalised data. Indeed, many automated generalisation systems require…

Human-Computer Interaction · Computer Science 2012-04-20 Patrick Taillandier , Julien Gaffuri

Current state-of-the-art neural dialogue systems are mainly data-driven and are trained on human-generated responses. However, due to the subjectivity and open-ended nature of human conversations, the complexity of training dialogues varies…

Computation and Language · Computer Science 2020-03-17 Hengyi Cai , Hongshen Chen , Cheng Zhang , Yonghao Song , Xiaofang Zhao , Yangxi Li , Dongsheng Duan , Dawei Yin

In this paper, we describe a set of metrics for the evaluation of different dialogue management strategies in an implemented real-time spoken language system. The set of metrics we propose offers useful insights in evaluating how particular…

cmp-lg · Computer Science 2008-02-03 Morena Danieli , Elisabetta Gerbino

Dialogue summarization is abstractive in nature, making it suffer from factual errors. The factual correctness of summaries has the highest priority before practical applications. Many efforts have been made to improve faithfulness in text…

Computation and Language · Computer Science 2022-10-24 Bin Wang , Chen Zhang , Yan Zhang , Yiming Chen , Haizhou Li

Automatic evaluating the performance of Open-domain dialogue system is a challenging problem. Recent work in neural network-based metrics has shown promising opportunities for automatic dialogue evaluation. However, existing methods mainly…

Computation and Language · Computer Science 2018-05-09 Xiaowei Tong , Zhenxin Fu , Mingyue Shang , Dongyan Zhao , Rui Yan

While automatic performance metrics are crucial for machine learning of artificial human-like behaviour, the gold standard for evaluation remains human judgement. The subjective evaluation of artificial human-like behaviour in embodied…

Human-Computer Interaction · Computer Science 2021-08-16 Pieter Wolfert , Jeffrey M. Girard , Taras Kucherenko , Tony Belpaeme

Evaluating Natural Language Generation (NLG) is crucial for the practical adoption of AI, but has been a longstanding research challenge. While human evaluation is considered the de-facto standard, it is expensive and lacks scalability.…

Computation and Language · Computer Science 2025-08-20 Maria Paz Oliva , Adriana Correia , Ivan Vankov , Viktor Botev

Automatic evaluation is beneficial for open-domain dialog system development. However, standard word-overlap metrics (BLEU, ROUGE) do not correlate well with human judgements of open-domain dialog systems. In this work we propose to use the…

Computation and Language · Computer Science 2022-02-18 Sarik Ghazarian , Behnam Hedayatnia , Alexandros Papangelis , Yang Liu , Dilek Hakkani-Tur

Evaluating text summarization is a challenging problem, and existing evaluation metrics are far from satisfactory. In this study, we explored ChatGPT's ability to perform human-like summarization evaluation using four human evaluation…

Computation and Language · Computer Science 2023-04-06 Mingqi Gao , Jie Ruan , Renliang Sun , Xunjian Yin , Shiping Yang , Xiaojun Wan

Today, large language models are widely used as judges to evaluate responses from other language models. Hence, it is imperative to benchmark and improve these LLM-judges on real-world language model usage: a typical human-assistant…

Computation and Language · Computer Science 2025-05-28 Sahana Ramnath , Anurag Mudgil , Brihi Joshi , Skyler Hallinan , Xiang Ren