English
Related papers

Related papers: Spectral Editing of Activations for Large Language…

200 papers

Recognizing daily activities with unobtrusive sensors in smart environments enables various healthcare applications. Monitoring how subjects perform activities at home and their changes over time can reveal early symptoms of health issues,…

Human-Computer Interaction · Computer Science 2024-08-14 Michele Fiori , Gabriele Civitarese , Claudio Bettini

Building helpful and harmless large language models (LLMs) requires effective model alignment approach based on human instructions and feedback, which necessitates high-quality human-labeled data. Constructing such datasets is often…

Computation and Language · Computer Science 2025-05-07 Junlin Wang , Roy Xie , Shang Zhu , Jue Wang , Ben Athiwaratkun , Bhuwan Dhingra , Shuaiwen Leon Song , Ce Zhang , James Zou

Large language models (LLMs) have achieved remarkable performance across many tasks, yet aligning them with desired behaviors remains challenging. Activation intervention has emerged as an effective and economical method to modify the…

Computation and Language · Computer Science 2025-02-26 Weixuan Wang , Jingyuan Yang , Wei Peng

While advances in fairness and alignment have helped mitigate overt biases exhibited by large language models (LLMs) when explicitly prompted, we hypothesize that these models may still exhibit implicit biases when simulating human…

Computation and Language · Computer Science 2025-01-30 Yuxuan Li , Hirokazu Shirado , Sauvik Das

Large language models (LLMs) struggle with hallucinations due to false or outdated knowledge. Given the high resource demands of retraining these models, there is an increasing focus on developing model editing. However, the general…

Computation and Language · Computer Science 2026-04-13 Hao-Xiang Xu , Jun-Yu Ma , Zhen-Hua Ling , Ningyu Zhang , Jia-Chen Gu

This is the first work to look at the application of large language models (LLMs) for the purpose of model space edits in automated planning tasks. To set the stage for this union, we explore two different flavors of model space problems…

Artificial Intelligence · Computer Science 2024-03-06 Turgay Caglar , Sirine Belhaj , Tathagata Chakraborti , Michael Katz , Sarath Sreedharan

Text animation, a foundational element in video creation, enables efficient and cost-effective communication, thriving in advertisements, journalism, and social media. However, traditional animation workflows present significant usability…

Human-Computer Interaction · Computer Science 2025-06-13 Bao Zhang , Zihan Li , Zhenglei Liu , Huanchen Wang , Yuxin Ma

Large Language Models (LLMs) often exhibit strong linguistic abilities while remaining unreliable on multi-step reasoning tasks, particularly when deployed without additional training or fine-tuning. In this work, we study inference-time…

Computation and Language · Computer Science 2026-03-24 Vinay Sharma , Manish Jain

Large language models (LLMs) commonly risk copyright infringement by reproducing protected content verbatim or with insufficient transformative modifications, posing significant ethical, legal, and practical concerns. Current inference-time…

Computation and Language · Computer Science 2025-06-02 Aakash Sen Sharma , Debdeep Sanyal , Priyansh Srivastava , Sundar Atreya H. , Shirish Karande , Mohan Kankanhalli , Murari Mandal

LLMs increasingly require surgical model editing to enhance domain-specific capabilities without incurring the computational cost or catastrophic forgetting associated with full fine-tuning. Sparse Autoencoders (SAEs) have emerged as a…

Machine Learning · Computer Science 2026-05-28 Li Lei , Madalina Ciobanu , Qingqing Mao , Ritankar Das

This research explores strategies for steering the output of large language models (LLMs) towards specific styles, such as sentiment, emotion, or writing style, by adding style vectors to the activations of hidden layers during text…

Computation and Language · Computer Science 2024-02-05 Kai Konen , Sophie Jentzsch , Diaoulé Diallo , Peer Schütt , Oliver Bensch , Roxanne El Baff , Dominik Opitz , Tobias Hecking

Activation steering is a method for controlling Large Language Model (LLM) behavior by intervening in its internal representations to increase the alignment with a specific target feature direction. However, standard interventions, such as…

Machine Learning · Computer Science 2026-05-05 Tam Nguyen , Tu Anh Nguyen , Sina Alemohammad , Richard G. Baraniuk

Large Language Models (LLMs) often suffer from ''Reasoning Collapse'' on challenging mathematical reasoning tasks, where stochastic sampling produces lexical variations of the same erroneous logic rather than genuine semantic exploration.…

Artificial Intelligence · Computer Science 2026-04-30 Dayu Wang , Jiaye Yang , Weikang Li , Jiahui Liang , Yang Li , Deguo Xia , Jizhou Huang

Bias in AI systems, especially those relying on natural language data, raises ethical and practical concerns. Underrepresentation of certain groups often leads to uneven performance across demographics. Traditional fairness methods, such as…

Computation and Language · Computer Science 2025-10-16 Sai Suhruth Reddy Karri , Yashwanth Sai Nallapuneni , Laxmi Narasimha Reddy Mallireddy , Gopichand G

Large Language Models (LLMs) have fundamentally transformed the field of natural language processing; however, their vulnerability to biases presents a notable obstacle that threatens both fairness and trust. This review offers an extensive…

Computation and Language · Computer Science 2025-09-19 Kiana Kiashemshaki , Mohammad Jalili Torkamani , Negin Mahmoudi , Meysam Shirdel Bilehsavar

Large Language Models (LLMs) are widely used by software engineers for programming tasks. However, research shows that LLMs often lack a deep understanding of program semantics. Even minor changes to syntax, such as renaming variables, can…

Computation and Language · Computer Science 2025-10-06 Francesca Lucchetti , Arjun Guha

Large language models (LLMs) often exhibit hallucinations due to incorrect or outdated knowledge. Hence, model editing methods have emerged to enable targeted knowledge updates. To achieve this, a prevailing paradigm is the…

Computation and Language · Computer Science 2025-04-23 Junfeng Fang , Houcheng Jiang , Kun Wang , Yunshan Ma , Shi Jie , Xiang Wang , Xiangnan He , Tat-seng Chua

Large language models (LLMs), trained on large-scale text, have recently attracted significant attention for their strong performance across many tasks. Motivated by this, we investigate whether a text-trained LLM can help localize fake…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-13 Lin Zhang , Thomas Thebaud , Zexin Cai , Sanjeev Khudanpur , Daniel Povey , Leibny Paola García-Perera , Matthew Wiesner , Nicholas Andrews

Large Language Models (LLMs) exhibit world knowledge and inference capabilities, making them powerful tools for various applications. This paper proposes a feedback loop mechanism that leverages these capabilities to tune Evolution…

Machine Learning · Computer Science 2024-05-21 Oliver Kramer

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