English
Related papers

Related papers: Shifting Perspectives: Steering Vectors for Robust…

200 papers

Recent advancements in language models (LMs) have marked a shift toward the growing importance of post-training. Yet, post-training approaches such as supervised fine-tuning (SFT) do not guarantee the effective use of knowledge acquired…

Computation and Language · Computer Science 2025-10-30 Chunyuan Deng , Ruidi Chang , Hanjie Chen

Language models (LMs) have been shown to behave unexpectedly post-deployment. For example, new jailbreaks continually arise, allowing model misuse, despite extensive red-teaming and adversarial training from developers. Given most model…

Computation and Language · Computer Science 2024-06-25 Asa Cooper Stickland , Alexander Lyzhov , Jacob Pfau , Salsabila Mahdi , Samuel R. Bowman

Reflection, the ability of large language models (LLMs) to evaluate and revise their own reasoning, has been widely used to improve performance on complex reasoning tasks. Yet, most prior works emphasizes designing reflective prompting…

Machine Learning · Computer Science 2025-12-12 Fu-Chieh Chang , Yu-Ting Lee , Pei-Yuan Wu

A fundamental challenge in autonomous driving is the integration of high-level, semantic reasoning for long-tail events with low-level, reactive control for robust driving. While large vision-language models (VLMs) trained on web-scale data…

Multimodal Large Language Models (MLLMs) already achieve state-of-the-art results across a wide range of tasks and modalities. To push their reasoning ability further, recent studies explore advanced prompting schemes and post-training…

Artificial Intelligence · Computer Science 2025-09-09 Zhenyu Pan , Yutong Zhang , Jianshu Zhang , Haoran Lu , Haozheng Luo , Yuwei Han , Philip S. Yu , Manling Li , Han Liu

Large vision-language models (LVLMs) often hallucinate objects that are not present in the input image, largely because visual grounding weakens as decoding progresses. Existing inference-time mitigation methods modify logits or hidden…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Soumyadeep Jana , Pulkit Mittal , Sanasam Ranbir Singh

Steering methods influence Large Language Model behavior by identifying semantic directions in hidden representations, but are typically realized through inference-time activation interventions that apply a fixed, global modification to the…

Computation and Language · Computer Science 2026-03-04 Chung-En Sun , Ge Yan , Zimo Wang , Tsui-Wei Weng

Activation steering is a practical post-training model alignment technique to enhance the utility of Large Language Models (LLMs). Prior to deploying a model as a service, developers can steer a pre-trained model toward specific behavioral…

Cryptography and Security · Computer Science 2026-02-06 Chen Xiong , Zhiyuan He , Pin-Yu Chen , Ching-Yun Ko , Tsung-Yi Ho

This paper presents a systematic analysis of biases in open-source Large Language Models (LLMs), across gender, religion, and race. Our study evaluates bias in smaller-scale Llama and Gemma models using the SALT ($\textbf{S}$ocial…

Computation and Language · Computer Science 2025-02-19 Samee Arif , Zohaib Khan , Maaidah Kaleem , Suhaib Rashid , Agha Ali Raza , Awais Athar

Controlling multiple behavioral attributes in large language models (LLMs) at inference time is a challenging problem due to interference between attributes and the limitations of linear steering methods, which assume additive behavior in…

Machine Learning · Computer Science 2026-04-07 Narmeen Oozeer , Luke Marks , Shreyans Jain , Fazl Barez , Amirali Abdullah

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

Large Vision-Language Models (LVLMs) extend large language models with visual understanding, but remain vulnerable to hallucination, where outputs are fluent yet inconsistent with images. Recent studies link this issue to language bias-the…

Computation and Language · Computer Science 2026-05-26 Yangneng Chen , Jing Li

In the constantly changing field of data-driven decision making, accurately predicting future events is crucial for strategic planning in various sectors. The emergence of Large Language Models (LLMs) marks a significant advancement in this…

Computation and Language · Computer Science 2025-01-10 Tommaso Soru , Jim Marshall

Word embeddings have been shown to produce remarkable results in tackling a vast majority of NLP related tasks. Unfortunately, word embeddings also capture the stereotypical biases that are prevalent in society, affecting the predictive…

Computation and Language · Computer Science 2024-11-20 Navya Yarrabelly , Vinay Damodaran , Feng-Guang Su

As generative large language models (LLMs) grow more performant and prevalent, we must develop comprehensive enough tools to measure and improve their fairness. Different prompt-based datasets can be used to measure social bias across…

In this research, we introduce BEATS, a novel framework for evaluating Bias, Ethics, Fairness, and Factuality in Large Language Models (LLMs). Building upon the BEATS framework, we present a bias benchmark for LLMs that measure performance…

Computation and Language · Computer Science 2025-04-01 Alok Abhishek , Lisa Erickson , Tushar Bandopadhyay

Large Language Models (LLMs) are increasingly being used to autonomously evaluate the quality of content in communication systems, e.g., to assess responses in telecom customer support chatbots. However, the impartiality of these AI…

Artificial Intelligence · Computer Science 2026-03-03 Jiaxin Gao , Chen Chen , Yanwen Jia , Xueluan Gong , Kwok-Yan Lam , Qian Wang

With the rapid development of large language models (LLMs), they have significantly improved efficiency across a wide range of domains. However, recent studies have revealed that LLMs often exhibit gender bias, leading to serious social…

Computation and Language · Computer Science 2025-06-17 Xiaoqing Cheng , Hongying Zan , Lulu Kong , Jinwang Song , Min Peng

Recommender and search systems commonly rely on Learning To Rank models trained on logged user interactions to order items by predicted relevance. However, such interaction data is often subject to position bias, as users are more likely to…

Information Retrieval · Computer Science 2025-09-05 Aleksandr V. Petrov , Michael Murtagh , Karthik Nagesh

Recent work on activation and latent steering has demonstrated that modifying internal representations can effectively guide large language models (LLMs) toward improved reasoning and efficiency without additional training. However, most…

Machine Learning · Computer Science 2026-01-07 Tuc Nguyen , Thai Le