English
Related papers

Related papers: UnQovering Stereotyping Biases via Underspecified …

200 papers

It is well documented that NLP models learn social biases, but little work has been done on how these biases manifest in model outputs for applied tasks like question answering (QA). We introduce the Bias Benchmark for QA (BBQ), a dataset…

Computation and Language · Computer Science 2022-03-17 Alicia Parrish , Angelica Chen , Nikita Nangia , Vishakh Padmakumar , Jason Phang , Jana Thompson , Phu Mon Htut , Samuel R. Bowman

Bias and stereotypes in language models can cause harm, especially in sensitive areas like content moderation and decision-making. This paper addresses bias and stereotype detection by exploring how jointly learning these tasks enhances…

Computation and Language · Computer Science 2025-07-03 Aditya Tomar , Rudra Murthy , Pushpak Bhattacharyya

Post-training quantization reduces the computational cost of large language models but fundamentally alters their social biases in ways that aggregate metrics fail to capture. We present the first large-scale study of 50 quantized models…

Computation and Language · Computer Science 2026-02-09 Stanley Z. Hua , Sanae Lotfi , Irene Y. Chen

Question answering (QA) tasks have been posed using a variety of formats, such as extractive span selection, multiple choice, etc. This has led to format-specialized models, and even to an implicit division in the QA community. We argue…

Computation and Language · Computer Science 2020-10-08 Daniel Khashabi , Sewon Min , Tushar Khot , Ashish Sabharwal , Oyvind Tafjord , Peter Clark , Hannaneh Hajishirzi

As large language models (LLMs) have been used in many downstream tasks, the internal stereotypical representation may affect the fairness of the outputs. In this work, we introduce human knowledge into natural language interventions and…

Computation and Language · Computer Science 2024-02-20 Damin Zhang

The goal of question answering (QA) is to answer any question. However, major QA datasets have skewed distributions over gender, profession, and nationality. Despite that skew, model accuracy analysis reveals little evidence that accuracy…

Computation and Language · Computer Science 2021-09-14 Maharshi Gor , Kellie Webster , Jordan Boyd-Graber

Gender bias research has been pivotal in revealing undesirable behaviors in large language models, exposing serious gender stereotypes associated with occupations, and emotions. A key observation in prior work is that models reinforce…

Computation and Language · Computer Science 2024-05-02 Catarina G Belém , Preethi Seshadri , Yasaman Razeghi , Sameer Singh

This paper proposes two intuitive metrics, skew and stereotype, that quantify and analyse the gender bias present in contextual language models when tackling the WinoBias pronoun resolution task. We find evidence that gender stereotype…

Computation and Language · Computer Science 2021-02-17 Daniel de Vassimon Manela , David Errington , Thomas Fisher , Boris van Breugel , Pasquale Minervini

It is challenging to automatically evaluate the answer of a QA model at inference time. Although many models provide confidence scores, and simple heuristics can go a long way towards indicating answer correctness, such measures are heavily…

Computation and Language · Computer Science 2020-10-08 Lukas Muttenthaler , Isabelle Augenstein , Johannes Bjerva

Large Language Models (LLMs) are commonly used in Question Answering (QA) settings, increasingly in the natural sciences if not science at large. Reliable Uncertainty Quantification (UQ) is critical for the trustworthy uptake of generated…

Computation and Language · Computer Science 2026-02-03 Philip Müller , Nicholas Popovič , Michael Färber , Peter Steinbach

This work presents a comprehensive evaluation of how quantization affects model bias, with particular attention to its impact on individual demographic subgroups. We focus on weight and activation quantization strategies and examine their…

Computation and Language · Computer Science 2026-03-06 Federico Marcuzzi , Xuefei Ning , Roy Schwartz , Iryna Gurevych

Large Language Models increasingly suppress biased outputs when demographic identity is stated explicitly, yet may still exhibit implicit biases when identity is conveyed indirectly. Existing benchmarks use name based proxies to detect…

Computation and Language · Computer Science 2026-04-03 Bhaskara Hanuma Vedula , Darshan Anghan , Ishita Goyal , Ponnurangam Kumaraguru , Abhijnan Chakraborty

Gender, race and social biases have recently been detected as evident examples of unfairness in applications of Natural Language Processing. A key path towards fairness is to understand, analyse and interpret our data and algorithms. Recent…

Computation and Language · Computer Science 2021-05-06 Christine Basta , Marta R. Costa-jussà

Abusive language detection models tend to have a problem of being biased toward identity words of a certain group of people because of imbalanced training datasets. For example, "You are a good woman" was considered "sexist" when trained on…

Computation and Language · Computer Science 2018-08-23 Ji Ho Park , Jamin Shin , Pascale Fung

Large Language Models have been shown to demonstrate stereotypical biases in their representations and behavior due to the discriminative nature of the data that they have been trained on. Despite significant progress in the development of…

Computation and Language · Computer Science 2025-10-29 Kaveh Eskandari Miandoab , Mahammed Kamruzzaman , Arshia Gharooni , Gene Louis Kim , Vasanth Sarathy , Ninareh Mehrabi

The size of pretrained models is increasing, and so is their performance on a variety of NLP tasks. However, as their memorization capacity grows, they might pick up more social biases. In this work, we examine the connection between model…

Computation and Language · Computer Science 2022-06-22 Yarden Tal , Inbal Magar , Roy Schwartz

Uncertainty Quantification (UQ) research has primarily focused on closed-book factual question answering (QA), while contextual QA remains unexplored, despite its importance in real-world applications. In this work, we focus on UQ for the…

Many studies have shown various biases targeting different demographic groups in language models, amplifying discrimination and harming fairness. Recent parameter modification debiasing approaches significantly degrade core capabilities…

Computation and Language · Computer Science 2025-10-01 Dianqing Liu , Yi Liu , Guoqing Jin , Zhendong Mao

In this paper we motivate the causal mechanisms behind sample selection induced collider bias (selection collider bias) that can cause Large Language Models (LLMs) to learn unconditional dependence between entities that are unconditionally…

Computation and Language · Computer Science 2022-09-14 Emily McMilin

Gender bias in pretrained language models (PLMs) poses significant social and ethical challenges. Despite growing awareness, there is a lack of comprehensive investigation into how different models internally represent and propagate such…

Computation and Language · Computer Science 2025-03-11 Mahdi Zakizadeh , Mohammad Taher Pilehvar
‹ Prev 1 2 3 10 Next ›