English
Related papers

Related papers: Programming Refusal with Conditional Activation St…

200 papers

Having an LLM that aligns with human preferences is essential for accommodating individual needs, such as maintaining writing style or generating specific topics of interest. The majority of current alignment methods rely on fine-tuning or…

Computation and Language · Computer Science 2025-03-06 Bingqing Song , Boran Han , Shuai Zhang , Hao Wang , Haoyang Fang , Bonan Min , Yuyang Wang , Mingyi Hong

Large language models (LLMs) are increasingly paired with activation-based monitoring to detect and prevent harmful behaviors that may not be apparent at the surface-text level. However, existing activation safety approaches, trained on…

Artificial Intelligence · Computer Science 2026-05-01 Shir Rozenfeld , Rahul Pankajakshan , Itay Zloczower , Eyal Lenga , Gilad Gressel , Yisroel Mirsky

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

Researchers have been studying approaches to steer the behavior of Large Language Models (LLMs) and build personalized LLMs tailored for various applications. While fine-tuning seems to be a direct solution, it requires substantial…

Computation and Language · Computer Science 2024-07-31 Yuanpu Cao , Tianrong Zhang , Bochuan Cao , Ziyi Yin , Lu Lin , Fenglong Ma , Jinghui Chen

Reliable behavior control is central to deploying large language models (LLMs) on the web. Activation steering offers a tuning-free route to align attributes (e.g., truthfulness) that ensure trustworthy generation. Prevailing approaches…

Artificial Intelligence · Computer Science 2025-11-19 Manjiang Yu , Hongji Li , Priyanka Singh , Xue Li , Di Wang , Lijie Hu

Activation steering has emerged as a cost-effective paradigm for modifying large language model (LLM) behaviors. Existing methods typically intervene at the block level, steering the bundled activations of selected attention heads,…

Computation and Language · Computer Science 2026-02-05 Zijian Feng , Tianjiao Li , Zixiao Zhu , Hanzhang Zhou , Junlang Qian , Li Zhang , Jia Jim Deryl Chua , Lee Onn Mak , Gee Wah Ng , Kezhi Mao

Large Language Models (LLMs) are increasingly deployed in high-stakes decision-making contexts. While prior work has shown that LLMs exhibit cognitive biases behaviorally, whether these biases correspond to identifiable internal…

Artificial Intelligence · Computer Science 2026-04-03 Fan Huang , Songheng Zhang , Haewoon Kwak , Jisun An

Although achieving promising performance, recent analyses show that current generative large language models (LLMs) may still capture dataset biases and utilize them for generation, leading to poor generalizability and harmfulness of LLMs.…

Computation and Language · Computer Science 2024-09-02 Li Du , Zhouhao Sun , Xiao Ding , Yixuan Ma , Yang Zhao , Kaitao Qiu , Ting Liu , Bing Qin

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

Multi-agent debate has been shown to improve reasoning in large language models (LLMs). However, it is compute-intensive, requiring generation of long transcripts before answering questions. To address this inefficiency, we develop a…

Artificial Intelligence · Computer Science 2026-04-29 John Seon Keun Yi , Aaron Mueller , Dokyun Lee

Large language models (LLMs) can sometimes detect when they are being evaluated and adjust their behavior to appear more aligned, compromising the reliability of safety evaluations. In this paper, we show that adding a steering vector to an…

Computation and Language · Computer Science 2026-03-03 Tim Tian Hua , Andrew Qin , Samuel Marks , Neel Nanda

We introduce Mechanistic Error Reduction with Abstention (MERA), a principled framework for steering language models (LMs) to mitigate errors through selective, adaptive interventions. Unlike existing methods that rely on fixed, manually…

Machine Learning · Computer Science 2025-10-16 Anna Hedström , Salim I. Amoukou , Tom Bewley , Saumitra Mishra , Manuela Veloso

Language models (LMs) can be directed to perform target tasks by using labeled examples or natural language prompts. But selecting examples or writing prompts for can be challenging--especially in tasks that involve unusual edge cases,…

Computation and Language · Computer Science 2023-10-19 Belinda Z. Li , Alex Tamkin , Noah Goodman , Jacob Andreas

Language models are instruction-tuned to refuse harmful requests, but the mechanisms underlying this behavior remain poorly understood. Popular steering methods operate on the residual stream and degrade output coherence at high…

Machine Learning · Computer Science 2026-05-13 Sam Herring , Jake Naviasky , Karan Malhotra

Chain-of-Thought (CoT) reasoning is a critical capability for large language models (LLMs), enabling them to tackle com- plex multi-step tasks. While base LLMs, pre-trained on general text corpora, often struggle with reasoning due to a…

Computation and Language · Computer Science 2025-11-25 Zijian Wang , Yanxiang Ma , Chang Xu

Recent work on domain-specific reasoning with large language models (LLMs) often relies on training-intensive approaches that require parameter updates. While activation steering has emerged as a parameter efficient alternative, existing…

Artificial Intelligence · Computer Science 2026-01-21 Wencheng Ye , Xiaoyang Yuan , Yi Bin , Pengpeng Zeng , Hengyu Jin , Liang Peng , Heng Tao Shen

Recent progress in Multimodal Large Language Models (MLLMs) has unlocked powerful cross-modal reasoning abilities, but also raised new safety concerns, particularly when faced with adversarial multimodal inputs. To improve the safety of…

Computation and Language · Computer Science 2025-09-24 Lyucheng Wu , Mengru Wang , Ziwen Xu , Tri Cao , Nay Oo , Bryan Hooi , Shumin Deng

Text analysis of tabular data relies on two core operations: \emph{summarization} for corpus-level theme extraction and \emph{tagging} for row-level labeling. A critical limitation of employing large language models (LLMs) for these tasks…

Computation and Language · Computer Science 2026-04-23 Jinxiang Xie , Zihao Li , Wei He , Rui Ding , Shi Han , Dongmei Zhang

Aligning Large Language Models (LLMs) with specific personas typically relies on expensive and monolithic Supervised Fine-Tuning (SFT) or RLHF. While effective, these methods require training distinct models for every target personality…

Computation and Language · Computer Science 2026-03-05 Florian Hoppe , David Khachaturov , Robert Mullins , Mark Huasong Meng

Large language model-based multi-agent systems (LLM-MAS) effectively accomplish complex and dynamic tasks through inter-agent communication, but this reliance introduces substantial safety vulnerabilities. Existing attack methods targeting…

Cryptography and Security · Computer Science 2025-08-06 Bingyu Yan , Ziyi Zhou , Xiaoming Zhang , Chaozhuo Li , Ruilin Zeng , Yirui Qi , Tianbo Wang , Litian Zhang
‹ Prev 1 4 5 6 7 8 10 Next ›