English
Related papers

Related papers: REFINE-LM: Mitigating Language Model Stereotypes v…

200 papers

Reinforcement learning (RL) has emerged as a powerful post-training technique to incentivize the reasoning ability of large language models (LLMs). However, LLMs can respond very inconsistently to RL finetuning: some show substantial…

Machine Learning · Computer Science 2025-10-07 Zhepeng Cen , Yihang Yao , William Han , Zuxin Liu , Ding Zhao

Large language models (LLMs) can transform education, but their optimization for direct question-answering often undermines effective pedagogy which requires strategically withholding answers. To mitigate this, we propose an online…

Computation and Language · Computer Science 2025-10-14 David Dinucu-Jianu , Jakub Macina , Nico Daheim , Ido Hakimi , Iryna Gurevych , Mrinmaya Sachan

Although value-aligned language models (LMs) appear unbiased in explicit bias evaluations, they often exhibit stereotypes in implicit word association tasks, raising concerns about their fair usage. We investigate the mechanisms behind this…

Computation and Language · Computer Science 2025-06-10 Lihao Sun , Chengzhi Mao , Valentin Hofmann , Xuechunzi Bai

Reinforcement learning (RL) has demonstrated potential in enhancing the reasoning capabilities of large language models (LLMs), but such training typically demands substantial efforts in creating and annotating data. In this work, we…

Computation and Language · Computer Science 2025-10-06 Hangfan Zhang , Siyuan Xu , Zhimeng Guo , Huaisheng Zhu , Shicheng Liu , Xinrun Wang , Qiaosheng Zhang , Yang Chen , Peng Ye , Lei Bai , Shuyue Hu

Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences. However, a major challenge arises from the sparsity of these reward signals - typically, there is only a single reward…

Computation and Language · Computer Science 2024-02-20 Meng Cao , Lei Shu , Lei Yu , Yun Zhu , Nevan Wichers , Yinxiao Liu , Lei Meng

In-context learning (ICL) of large language models (LLMs) has attracted increasing attention in the community where LLMs make predictions only based on instructions augmented with a few examples. Existing example selection methods for ICL…

Computation and Language · Computer Science 2024-08-26 Haowei Du , Dongyan Zhao

Large language models (LLMs) are increasingly deployed in high-stakes hiring applications, making decisions that directly impact people's careers and livelihoods. While prior studies suggest simple anti-bias prompts can eliminate…

Machine Learning · Computer Science 2025-06-13 Adam Karvonen , Samuel Marks

Vision-language models can encode societal biases and stereotypes, but there are challenges to measuring and mitigating these multimodal harms due to lacking measurement robustness and feature degradation. To address these challenges, we…

Machine Learning · Computer Science 2022-10-27 Hugo Berg , Siobhan Mackenzie Hall , Yash Bhalgat , Wonsuk Yang , Hannah Rose Kirk , Aleksandar Shtedritski , Max Bain

Artificial Intelligence has the capacity to amplify and perpetuate societal biases and presents profound ethical implications for society. Gender bias has been identified in the context of employment advertising and recruitment tools, due…

Computation and Language · Computer Science 2020-05-19 Susan Leavy , Gerardine Meaney , Karen Wade , Derek Greene

Large language models (LLMs) have achieved impressive performance on various natural language generation tasks. Nonetheless, they suffer from generating negative and harmful contents that are biased against certain demographic groups (e.g.,…

Machine Learning · Computer Science 2024-06-05 Tianci Liu , Haoyu Wang , Shiyang Wang , Yu Cheng , Jing Gao

In the era of Large Language Models (LLMs), alignment has emerged as a fundamental yet challenging problem in the pursuit of more reliable, controllable, and capable machine intelligence. The recent success of reasoning models and…

Machine Learning · Computer Science 2025-07-18 Hao Sun , Mihaela van der Schaar

Reinforcement learning (RL) has been widely used in training large language models (LLMs) for preventing unexpected outputs, eg reducing harmfulness and errors. However, existing RL methods mostly adopt the instance-level reward, which is…

Computation and Language · Computer Science 2024-06-18 Zhipeng Chen , Kun Zhou , Wayne Xin Zhao , Junchen Wan , Fuzheng Zhang , Di Zhang , Ji-Rong Wen

Large language models (LLMs) offer significant potential as tools to support an expanding range of decision-making tasks. Given their training on human (created) data, LLMs have been shown to inherit societal biases against protected…

Artificial Intelligence · Computer Science 2024-10-07 Jessica Echterhoff , Yao Liu , Abeer Alessa , Julian McAuley , Zexue He

Large Language Models (LLMs) have made substantial progress in the past several months, shattering state-of-the-art benchmarks in many domains. This paper investigates LLMs' behavior with respect to gender stereotypes, a known issue for…

Computation and Language · Computer Science 2023-08-30 Hadas Kotek , Rikker Dockum , David Q. Sun

Pre-trained Large Language Models (LLMs) have significantly advanced natural language processing capabilities but are susceptible to biases present in their training data, leading to unfair outcomes in various applications. While numerous…

Computation and Language · Computer Science 2024-03-04 Sana Ebrahimi , Kaiwen Chen , Abolfazl Asudeh , Gautam Das , Nick Koudas

Large Language Models (LLMs) offer the potential to automate hiring by matching job descriptions with candidate resumes, streamlining recruitment processes, and reducing operational costs. However, biases inherent in these models may lead…

Computation and Language · Computer Science 2025-03-26 Hayate Iso , Pouya Pezeshkpour , Nikita Bhutani , Estevam Hruschka

Several recent studies have shown that strong natural language understanding (NLU) models are prone to relying on unwanted dataset biases without learning the underlying task, resulting in models that fail to generalize to out-of-domain…

Computation and Language · Computer Science 2020-04-27 Rabeeh Karimi Mahabadi , Yonatan Belinkov , James Henderson

We propose selective debiasing -- an inference-time safety mechanism designed to enhance the overall model quality in terms of prediction performance and fairness, especially in scenarios where retraining the model is impractical. The…

Computation and Language · Computer Science 2025-03-12 Gleb Kuzmin , Neemesh Yadav , Ivan Smirnov , Timothy Baldwin , Artem Shelmanov

Advancements in Large Language Models (LLMs) have increased the performance of different natural language understanding as well as generation tasks. Although LLMs have breached the state-of-the-art performance in various tasks, they often…

Computation and Language · Computer Science 2025-05-28 Charaka Vinayak Kumar , Ashok Urlana , Gopichand Kanumolu , Bala Mallikarjunarao Garlapati , Pruthwik Mishra

Fine-tuned language models have been shown to exhibit biases against protected groups in a host of modeling tasks such as text classification and coreference resolution. Previous works focus on detecting these biases, reducing bias in data…

Computation and Language · Computer Science 2021-04-13 Xisen Jin , Francesco Barbieri , Brendan Kennedy , Aida Mostafazadeh Davani , Leonardo Neves , Xiang Ren