English
Related papers

Related papers: ABCD: All Biases Come Disguised

200 papers

Multimodal Large Language Models (MLLMs) demonstrate strong capabilities in handling image-text inputs. A common way to assess this ability is through multiple-choice Visual Question Answering (VQA). Earlier works have already revealed that…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Fabio Rosenthal , Sebastian Schmidt , Thorsten Graf , Thorsten Bagodonat , Stephan Günnemann , Leo Schwinn

Safety-aligned large language models (LLMs) are becoming increasingly widespread, especially in sensitive applications where fairness is essential and biased outputs can cause significant harm. However, evaluating the fairness of models is…

Computation and Language · Computer Science 2026-03-19 Rom Himelstein , Amit LeVi , Brit Youngmann , Yaniv Nemcovsky , Avi Mendelson

We introduce \emph{Metric-Fair Prompting}, a fairness-aware prompting framework that guides large language models (LLMs) to make decisions under metric-fairness constraints. In the application of multiple-choice medical question answering,…

Computation and Language · Computer Science 2025-12-09 Jing Wang , Jie Shen , Xing Niu , Tong Zhang , Jeremy Weiss

Multiple-choice questions (MCQs) are widely used in the evaluation of large language models (LLMs) due to their simplicity and efficiency. However, there are concerns about whether MCQs can truly measure LLM's capabilities, particularly in…

Computation and Language · Computer Science 2024-05-24 Wangyue Li , Liangzhi Li , Tong Xiang , Xiao Liu , Wei Deng , Noa Garcia

Over-prompting, a phenomenon where excessive examples in prompts lead to diminished performance in Large Language Models (LLMs), challenges the conventional wisdom about in-context few-shot learning. To investigate this few-shot dilemma, we…

Computation and Language · Computer Science 2025-09-17 Yongjian Tang , Doruk Tuncel , Christian Koerner , Thomas Runkler

Multi-label learning often requires identifying all relevant labels for training instances, but collecting full label annotations is costly and labor-intensive. In many datasets, only a single positive label is annotated per training…

Machine Learning · Computer Science 2025-09-16 Misgina Tsighe Hagos , Claes Lundström

Few-shot or zero-shot fact verification only relies on a few or no labeled training examples. In this paper, we propose a novel method called ProToCo, to \underline{Pro}mpt pre-trained language models (PLMs) \underline{To} be…

Computation and Language · Computer Science 2023-06-06 Fengzhu Zeng , Wei Gao

Generative large language models (LLMs) have been shown to exhibit harmful biases and stereotypes. While safety fine-tuning typically takes place in English, if at all, these models are being used by speakers of many different languages.…

Computation and Language · Computer Science 2024-07-18 Vera Neplenbroek , Arianna Bisazza , Raquel Fernández

Few-shot named entity recognition (NER) targets generalizing to unseen labels and/or domains with few labeled examples. Existing metric learning methods compute token-level similarities between query and support sets, but are not able to…

Computation and Language · Computer Science 2022-11-09 Yanru Chen , Yanan Zheng , Zhilin Yang

With the success of pre-trained visual-language (VL) models such as CLIP in visual representation tasks, transferring pre-trained models to downstream tasks has become a crucial paradigm. Recently, the prompt tuning paradigm, which draws…

Computer Vision and Pattern Recognition · Computer Science 2023-12-14 Jingsheng Gao , Jiacheng Ruan , Suncheng Xiang , Zefang Yu , Ke Ji , Mingye Xie , Ting Liu , Yuzhuo Fu

The rapid development of LLMs has sparked extensive research into their factual knowledge. Current works find that LLMs fall short on questions around low-frequency entities. However, such proofs are unreliable since the questions can…

Computation and Language · Computer Science 2025-05-27 Qing Zong , Zhaowei Wang , Tianshi Zheng , Xiyu Ren , Yangqiu Song

Unsupervised commonsense question answering is appealing since it does not rely on any labeled task data. Among existing work, a popular solution is to use pre-trained language models to score candidate choices directly conditioned on the…

Computation and Language · Computer Science 2021-06-01 Yilin Niu , Fei Huang , Jiaming Liang , Wenkai Chen , Xiaoyan Zhu , Minlie Huang

Commonsense question-answering (QA) tasks, in the form of benchmarks, are constantly being introduced for challenging and comparing commonsense QA systems. The benchmarks provide question sets that systems' developers can use to train and…

Artificial Intelligence · Computer Science 2020-12-23 Henrique Santos , Minor Gordon , Zhicheng Liang , Gretchen Forbush , Deborah L. McGuinness

To advance argumentative stance prediction as a multimodal problem, the First Shared Task in Multimodal Argument Mining hosted stance prediction in crucial social topics of gun control and abortion. Our exploratory study attempts to…

Computation and Language · Computer Science 2023-10-12 Arushi Sharma , Abhibha Gupta , Maneesh Bilalpur

Despite growing interest in using Large Language Models (LLMs) for educational assessment, it remains unclear how closely they align with human scoring. We present a systematic evaluation of instruction-tuned LLMs across three open…

Computation and Language · Computer Science 2026-04-02 Filip J. Kucia , Anirban Chakraborty , Anna Wróblewska

Standard benchmarks of bias and fairness in large language models (LLMs) measure the association between the user attributes stated or implied by a prompt and the LLM's short text response, but human-AI interaction increasingly requires…

Computation and Language · Computer Science 2025-06-06 Kristian Lum , Jacy Reese Anthis , Kevin Robinson , Chirag Nagpal , Alexander D'Amour

Performance of Large Language Models (LLMs) on multiple-choice tasks differs markedly between symbol-based and cloze-style evaluation formats. The observed discrepancies are systematically attributable to task characteristics: natural…

Computation and Language · Computer Science 2026-02-02 Joonhak Lee , Sungmok Jung , Jongyeon Park , Jaejin Lee

Recent research has revealed that deep neural networks often take dataset biases as a shortcut to make decisions rather than understand tasks, leading to failures in real-world applications. In this study, we focus on the spurious…

Computation and Language · Computer Science 2023-06-23 Yanrui Du , Jing Yan , Yan Chen , Jing Liu , Sendong Zhao , Qiaoqiao She , Hua Wu , Haifeng Wang , Bing Qin

Recent vision-language models (VLMs) achieve strong zero-shot performance via large-scale image-text pretraining and have been widely adopted in medical image analysis. However, existing VLMs remain notably weak at understanding negated…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Tae Hun Kim , Hyun Gyu Lee

Text embedding models are designed for sentence-level applications like retrieval and semantic similarity, and are primarily evaluated on sentence-level benchmarks. Their behavior on isolated words is less understood. We show that simply…

Computation and Language · Computer Science 2025-12-09 Rajeev Ranjan