English
Related papers

Related papers: Shifting Perspectives: Steering Vectors for Robust…

200 papers

Multi-modal large language models (MLLMs), such as GPT-4o, excel at integrating text and visual data but face systematic challenges when interpreting ambiguous or incomplete visual stimuli. This study leverages statistical modeling to…

Machine Learning · Computer Science 2024-12-09 Ching-Yi Wang

Large Language Models (LLMs) are powerful tools with the potential to benefit society immensely, yet, they have demonstrated biases that perpetuate societal inequalities. Despite significant advancements in bias mitigation techniques using…

Computation and Language · Computer Science 2024-09-24 Deonna M. Owens , Ryan A. Rossi , Sungchul Kim , Tong Yu , Franck Dernoncourt , Xiang Chen , Ruiyi Zhang , Jiuxiang Gu , Hanieh Deilamsalehy , Nedim Lipka

Steering language models (LMs) by modifying internal activations is a popular approach for controlling text generation. Unsupervised dictionary learning methods, e.g., sparse autoencoders, can be scaled to produce many steering vectors, but…

Computation and Language · Computer Science 2025-06-05 Jiuding Sun , Sidharth Baskaran , Zhengxuan Wu , Michael Sklar , Christopher Potts , Atticus Geiger

Large language models (LLMs) excel at diverse tasks, but their deployment on resource-constrained devices remains challenging. Existing methods like quantization, pruning, and distillation can reduce memory footprint but often demand…

Artificial Intelligence · Computer Science 2025-12-23 Siddharth Tandon

Language models (LMs) automatically learn word embeddings during pre-training on language corpora. Although word embeddings are usually interpreted as feature vectors for individual words, their roles in language model generation remain…

Computation and Language · Computer Science 2024-06-07 Chi Han , Jialiang Xu , Manling Li , Yi Fung , Chenkai Sun , Nan Jiang , Tarek Abdelzaher , Heng Ji

Providing high-quality feedback to Large Language Models (LLMs) on a diverse training distribution can be difficult and expensive, and providing feedback only on a narrow distribution can result in unintended generalizations. To better…

Computation and Language · Computer Science 2026-03-02 Constanza Fierro , Fabien Roger

Stereotype biases in Large Multimodal Models (LMMs) perpetuate harmful societal prejudices, undermining the fairness and equity of AI applications. As LMMs grow increasingly influential, addressing and mitigating inherent biases related to…

Computer Vision and Pattern Recognition · Computer Science 2026-01-19 Vishal Narnaware , Ashmal Vayani , Rohit Gupta , Sirnam Swetha , Mubarak Shah

Protein Language Models (PLMs), pre-trained on extensive evolutionary data from natural proteins, have emerged as indispensable tools for protein design. While powerful, PLMs often struggle to produce proteins with precisely specified…

Biomolecules · Quantitative Biology 2025-09-15 Long-Kai Huang , Rongyi Zhu , Bing He , Jianhua Yao

Vision-Language Models (VLMs) and generative image models have achieved remarkable performance across multimodal tasks, yet their robustness and fairness under input transformations remain insufficiently explored. This work investigates…

Computer Vision and Pattern Recognition · Computer Science 2026-01-15 Tarannum Mithila

Large language models (LLMs) are prone to capturing biases from training corpus, leading to potential negative social impacts. Existing prompt-based debiasing methods exhibit instability due to their sensitivity to prompt changes, while…

Computation and Language · Computer Science 2025-07-08 Yichen Li , Zhiting Fan , Ruizhe Chen , Xiaotang Gai , Luqi Gong , Yan Zhang , Zuozhu Liu

Software bias is an increasingly important operational concern for software engineers. We present a large-scale, comprehensive empirical study of 17 representative bias mitigation methods for Machine Learning (ML) classifiers, evaluated…

Software Engineering · Computer Science 2023-02-13 Zhenpeng Chen , Jie M. Zhang , Federica Sarro , Mark Harman

Large Language Models (LLMs) have emerged as promising solutions for a variety of medical and clinical decision support applications. However, LLMs are often subject to different types of biases, which can lead to unfair treatment of…

Computation and Language · Computer Science 2024-08-23 Raphael Poulain , Hamed Fayyaz , Rahmatollah Beheshti

Large language models (LLMs) can pass explicit social bias tests but still harbor implicit biases, similar to humans who endorse egalitarian beliefs yet exhibit subtle biases. Measuring such implicit biases can be a challenge: as LLMs…

Computers and Society · Computer Science 2024-05-24 Xuechunzi Bai , Angelina Wang , Ilia Sucholutsky , Thomas L. Griffiths

Recent advancements in Large Language Models(LLMs) have been notable, yet widespread enterprise adoption remains limited due to various constraints. This paper examines bias in LLMs-a crucial issue affecting their usability, reliability,…

Artificial Intelligence · Computer Science 2026-05-28 Vishal Mirza , Rahul Kulkarni , Aakanksha Jadhav

Human action recognition models often rely on background cues rather than human movement and pose to make predictions, a behavior known as background bias. We present a systematic analysis of background bias across classification models,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-23 Ellie Zhou , Jihoon Chung , Olga Russakovsky

Interventions in language models (LMs) are applied strategically to steer model behavior during the forward pass. Learnable interventions, also known as representation fine-tuning, aim to apply pointwise control within the concept subspace…

Computation and Language · Computer Science 2025-06-10 Chunyuan Deng , Ruidi Chang , Hanjie Chen

Large language models (LLMs) can memorize and reproduce training sequences verbatim -- a tendency that undermines both generalization and privacy. Existing mitigation methods apply interventions uniformly, degrading performance on the…

Machine Learning · Computer Science 2026-02-10 Xuanqi Zhang , Haoyang Shang , Xiaoxiao Li

Agents backed by large language models (LLMs) increasingly rely on external tools drawn from marketplaces where multiple providers offer functionally equivalent options. This raises a critical fairness concern: systematic bias in tool…

Artificial Intelligence · Computer Science 2026-03-12 Thierry Blankenstein , Jialin Yu , Zixuan Li , Vassilis Plachouras , Sunando Sengupta , Philip Torr , Yarin Gal , Alasdair Paren , Adel Bibi

Large Language Models (LLMs) are increasingly used in decision-making, yet their susceptibility to cognitive biases remains a pressing challenge. This study explores how personality traits influence these biases and evaluates the…

Artificial Intelligence · Computer Science 2025-02-21 Jiangen He , Jiqun Liu

As Vision Language Models (VLMs) are deployed across safety-critical applications, understanding and controlling their behavioral patterns has become increasingly important. Existing behavioral control methods face significant limitations:…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Ravikumar Balakrishnan , Mansi Phute