English
Related papers

Related papers: Unsupervised Concept Vector Extraction for Bias Co…

200 papers

Prior work on controllable text generation has focused on learning how to control language models through trainable decoding, smart-prompt design, or fine-tuning based on a desired objective. We hypothesize that the information needed to…

Computation and Language · Computer Science 2022-05-12 Nishant Subramani , Nivedita Suresh , Matthew E. Peters

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

Large Language Models (LLMs) are known to exhibit social, demographic, and gender biases, often as a consequence of the data on which they are trained. In this work, we adopt a mechanistic interpretability approach to analyze how such…

Computation and Language · Computer Science 2025-06-09 Bhavik Chandna , Zubair Bashir , Procheta Sen

Large Language Models (LLMs) have revolutionized natural language processing, but their susceptibility to biases poses significant challenges. This comprehensive review examines the landscape of bias in LLMs, from its origins to current…

Computation and Language · Computer Science 2026-05-04 Yufei Guo , Muzhe Guo , Juntao Su , Zhou Yang , Mengqiu Zhu , Hongfei Li , Mengyang Qiu , Shuo Shuo Liu

Large language models (LLMs) have garnered significant attention for their remarkable performance in a continuously expanding set of natural language processing tasks. However, these models have been shown to harbor inherent societal…

Computation and Language · Computer Science 2023-10-16 Abel Salinas , Louis Penafiel , Robert McCormack , Fred Morstatter

Large Language Models (LLMs) have shown impressive performance in natural language tasks, but their outputs can exhibit undesirable attributes or biases. Existing methods for steering LLMs toward desired attributes often assume unbiased…

Computation and Language · Computer Science 2024-09-05 Zhixuan Chu , Yan Wang , Longfei Li , Zhibo Wang , Zhan Qin , Kui Ren

As large language models (LLMs) become increasingly embedded in products used by millions, their outputs may influence individual beliefs and, cumulatively, shape public opinion. If the behavior of LLMs can be intentionally steered toward…

Computation and Language · Computer Science 2025-09-17 Paul Kröger , Emilio Barkett

Changing the behavior of large language models (LLMs) can be as straightforward as editing the Transformer's residual streams using appropriately constructed "steering vectors." These modifications to internal neural activations, a form of…

Computation and Language · Computer Science 2025-05-20 Jian-Qiao Zhu , Haijiang Yan , Thomas L. Griffiths

With the advent of Large Language Models (LLMs) possessing increasingly impressive capabilities, a number of Large Vision-Language Models (LVLMs) have been proposed to augment LLMs with visual inputs. Such models condition generated text on…

Computer Vision and Pattern Recognition · Computer Science 2025-05-01 Phillip Howard , Kathleen C. Fraser , Anahita Bhiwandiwalla , Svetlana Kiritchenko

We present a novel approach to bias mitigation in large language models (LLMs) by applying steering vectors to modify model activations in forward passes. We compute 8 steering vectors, each corresponding to a different social bias axis,…

Machine Learning · Computer Science 2026-03-31 Zara Siddique , Irtaza Khalid , Liam D. Turner , Luis Espinosa-Anke

Steering methods have emerged as effective and targeted tools for guiding large language models' (LLMs) behavior without modifying their parameters. Multimodal large language models (MLLMs), however, do not currently enjoy the same suite of…

Machine Learning · Computer Science 2025-05-21 Woody Haosheng Gan , Deqing Fu , Julian Asilis , Ollie Liu , Dani Yogatama , Vatsal Sharan , Robin Jia , Willie Neiswanger

Large-language models are capable of completing a variety of tasks, but remain unpredictable and intractable. Representation engineering seeks to resolve this problem through a new approach utilizing samples of contrasting inputs to detect…

Artificial Intelligence · Computer Science 2025-02-26 Lukasz Bartoszcze , Sarthak Munshi , Bryan Sukidi , Jennifer Yen , Zejia Yang , David Williams-King , Linh Le , Kosi Asuzu , Carsten Maple

Large Language Models (LLMs) have excelled at language understanding and generating human-level text. However, even with supervised training and human alignment, these LLMs are susceptible to adversarial attacks where malicious users can…

Computation and Language · Computer Science 2024-08-08 Shachi H Kumar , Saurav Sahay , Sahisnu Mazumder , Eda Okur , Ramesh Manuvinakurike , Nicole Beckage , Hsuan Su , Hung-yi Lee , Lama Nachman

As Large Language Models (LLMs) continue to evolve, they are increasingly being employed in numerous studies to simulate societies and execute diverse social tasks. However, LLMs are susceptible to societal biases due to their exposure to…

Computation and Language · Computer Science 2024-10-04 Angana Borah , Rada Mihalcea

Social biases can manifest in language agency. However, very limited research has investigated such biases in Large Language Model (LLM)-generated content. In addition, previous works often rely on string-matching techniques to identify…

Computation and Language · Computer Science 2025-06-03 Yixin Wan , Kai-Wei Chang

Although prior work on bias mitigation has focused on promoting social equality and demographic parity, less attention has been given to aligning LLM's outputs to desired distributions. For example, we might want to align a model with…

Computation and Language · Computer Science 2025-10-09 Ingroj Shrestha , Padmini Srinivasan

Large Language Models are increasingly employed in generating consumer product recommendations, yet their potential for embedding and amplifying gender and race biases remains underexplored. This paper serves as one of the first attempts to…

Computation and Language · Computer Science 2026-02-10 Ke Xu , Shera Potka , Alex Thomo

The use of language models (LMs) has increased considerably in recent years, and the biases and stereotypes in training data that are reflected in the LM outputs are causing social problems. In this paper, inspired by the task arithmetic,…

Computation and Language · Computer Science 2024-12-17 Daiki Shirafuji , Makoto Takenaka , Shinya Taguchi

Large language models (LLMs) are the foundation of the current successes of artificial intelligence (AI), however, they are unavoidably biased. To effectively communicate the risks and encourage mitigation efforts these models need adequate…

Computation and Language · Computer Science 2025-01-14 Carolin M. Schuster , Maria-Alexandra Dinisor , Shashwat Ghatiwala , Georg Groh

Large Language Models (LLMs) are prone to inheriting and amplifying societal biases embedded within their training data, potentially reinforcing harmful stereotypes related to gender, occupation, and other sensitive categories. This issue…

Computation and Language · Computer Science 2024-08-28 Atmika Gorti , Manas Gaur , Aman Chadha