English
Related papers

Related papers: Spurious Correlations in Reference-Free Evaluation…

200 papers

This work aims to employ natural language generation (NLG) to rapidly generate items for English language learning applications: this requires both language models capable of generating fluent, high-quality English, and to control the…

Computation and Language · Computer Science 2022-11-30 Kevin Stowe , Debanjan Ghosh , Mengxuan Zhao

Generative spoken language models pretrained on large-scale raw audio can continue a speech prompt with appropriate content while preserving attributes like speaker and emotion, serving as foundation models for spoken dialogue. In prior…

Computation and Language · Computer Science 2026-05-28 Chan-Jan Hsu , Liang-Hsuan Tseng , Yi-Cheng Lin , Yen-Chun Kuo , Ju-Chieh Chou , Kai-Wei Chang , Hung-yi Lee , Carlos Busso

Existing automatic evaluation metrics for open-domain dialogue response generation systems correlate poorly with human evaluation. We focus on evaluating response generation systems via response selection. To evaluate systems properly via…

Computation and Language · Computer Science 2020-04-30 Shiki Sato , Reina Akama , Hiroki Ouchi , Jun Suzuki , Kentaro Inui

Evaluation of natural language generation (NLG) is complex and multi-dimensional. Generated text can be evaluated for fluency, coherence, factuality, or any other dimensions of interest. Most frameworks that perform such multi-dimensional…

Computation and Language · Computer Science 2024-02-20 Sameer Jain , Vaishakh Keshava , Swarnashree Mysore Sathyendra , Patrick Fernandes , Pengfei Liu , Graham Neubig , Chunting Zhou

We investigate evaluation metrics for dialogue response generation systems where supervised labels, such as task completion, are not available. Recent works in response generation have adopted metrics from machine translation to compare a…

Computation and Language · Computer Science 2017-01-04 Chia-Wei Liu , Ryan Lowe , Iulian V. Serban , Michael Noseworthy , Laurent Charlin , Joelle Pineau

Is it possible to build a general and automatic natural language generation (NLG) evaluation metric? Existing learned metrics either perform unsatisfactorily or are restricted to tasks where large human rating data is already available. We…

Computation and Language · Computer Science 2022-10-27 Wenda Xu , Yilin Tuan , Yujie Lu , Michael Saxon , Lei Li , William Yang Wang

Conventional automatic evaluation metrics, such as BLEU and ROUGE, developed for natural language generation (NLG) tasks, are based on measuring the n-gram overlap between the generated and reference text. These simple metrics may be…

Computation and Language · Computer Science 2024-02-27 Zifan Wang , Kotaro Funakoshi , Manabu Okumura

Spurious correlations threaten the validity of statistical classifiers. While model accuracy may appear high when the test data is from the same distribution as the training data, it can quickly degrade when the test distribution changes.…

Machine Learning · Computer Science 2020-12-21 Zhao Wang , Aron Culotta

Many Natural Language Generation (NLG) tasks aim to generate a single output text given an input prompt. Other settings require the generation of multiple texts, e.g., for Synthetic Traffic Generation (STG). This generation task is crucial…

Computation and Language · Computer Science 2023-11-22 Simone Filice , Jason Ingyu Choi , Giuseppe Castellucci , Eugene Agichtein , Oleg Rokhlenko

Automatic evaluation metrics are indispensable for evaluating generated text. To date, these metrics have focused almost exclusively on the content selection aspect of the system output, ignoring the linguistic quality aspect altogether. We…

Computation and Language · Computer Science 2020-10-07 Wanzheng Zhu , Suma Bhat

To address the problem of NLP classifiers learning spurious correlations between training features and target labels, a common approach is to make the model's predictions invariant to these features. However, this can be counter-productive…

Machine Learning · Computer Science 2023-06-22 Parikshit Bansal , Amit Sharma

Natural Language Inference (NLI) models frequently rely on spurious correlations rather than semantic reasoning. Existing mitigation strategies often incur high annotation costs or trigger catastrophic forgetting during fine-tuning. We…

Computation and Language · Computer Science 2025-12-23 Christopher Román Jaimes

Text summarizing is a critical Natural Language Processing (NLP) task with applications ranging from information retrieval to content generation. Large Language Models (LLMs) have shown remarkable promise in generating fluent abstractive…

Computation and Language · Computer Science 2025-03-03 Colleen Gilhuly , Haleh Shahzad

As transparency becomes key for robotics and AI, it will be necessary to evaluate the methods through which transparency is provided, including automatically generated natural language (NL) explanations. Here, we explore parallels between…

Computation and Language · Computer Science 2021-07-08 Miruna Clinciu , Arash Eshghi , Helen Hastie

The natural language generation (NLG) component of a spoken dialogue system (SDS) usually needs a substantial amount of handcrafting or a well-labeled dataset to be trained on. These limitations add significantly to development costs and…

Computation and Language · Computer Science 2015-08-10 Tsung-Hsien Wen , Milica Gasic , Dongho Kim , Nikola Mrksic , Pei-Hao Su , David Vandyke , Steve Young

Despite demonstrating remarkable performance across a wide range of tasks, large language models (LLMs) have also been found to frequently produce outputs that are incomplete or selectively omit key information. In sensitive domains, such…

Computation and Language · Computer Science 2026-05-11 Adam Dejl , James Barry , Alessandra Pascale , Javier Carnerero Cano

Finetuning can cause spurious correlations to arise between non-essential features and the target labels, but benchmarks to study these effects involve contrived settings and narrow tasks. In contrast, we consider spurious correlations in…

Computer Vision and Pattern Recognition · Computer Science 2025-06-24 Yiwei Yang , Chung Peng Lee , Shangbin Feng , Dora Zhao , Bingbing Wen , Anthony Z. Liu , Yulia Tsvetkov , Bill Howe

Response diversity has become an important criterion for evaluating the quality of open-domain dialogue generation models. However, current evaluation metrics for response diversity often fail to capture the semantic diversity of generated…

Computation and Language · Computer Science 2022-10-25 Seungju Han , Beomsu Kim , Buru Chang

Natural language understanding (NLU) models tend to rely on spurious correlations (i.e., dataset bias) to achieve high performance on in-distribution datasets but poor performance on out-of-distribution ones. Most of the existing debiasing…

Computation and Language · Computer Science 2022-09-14 Shihan Dou , Rui Zheng , Ting Wu , SongYang Gao , Junjie Shan , Qi Zhang , Yueming Wu , Xuanjing Huang

Advancements in dialogue systems powered by large language models (LLMs) have outpaced the development of reliable evaluation metrics, particularly for diverse and creative responses. We present a benchmark for evaluating the robustness of…

Computation and Language · Computer Science 2025-01-14 Justin Vasselli , Adam Nohejl , Taro Watanabe