English
Related papers

Related papers: Minimizing Collateral Damage in Activation Steerin…

200 papers

Large Language Models (LLMs) often struggle with deductive judgment in syllogistic reasoning, systematically conflating semantic plausibility with formal validity a phenomenon known as content effect. This bias persists even when models…

Computation and Language · Computer Science 2026-02-03 Gabriele Maraia , Marco Valentino , Fabio Massimo Zanzotto , Leonardo Ranaldi

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

Backdoor attacks compromise the integrity and reliability of machine learning models by embedding a hidden trigger during the training process, which can later be activated to cause unintended misbehavior. We propose a novel backdoor…

Computer Vision and Pattern Recognition · Computer Science 2024-10-01 Felix Hsieh , Huy H. Nguyen , AprilPyone MaungMaung , Dmitrii Usynin , Isao Echizen

Not a day goes by without hearing about the impressive feats of large language models (LLMs), and equally, not a day passes without hearing about their challenges. LLMs are notoriously vulnerable to biases in their dataset, leading to…

Computation and Language · Computer Science 2025-03-12 Sayem Mohammad Imtiaz , Astha Singh , Fraol Batole , Hridesh Rajan

Safety alignment in Large Language Models (LLMs) remains highly fragile during fine-tuning, where even benign adaptation can degrade pre-trained refusal behaviors and enable harmful responses. Existing defenses typically constrain either…

Artificial Intelligence · Computer Science 2026-04-15 Songping Peng , Zhiheng Zhang , Daojian Zeng , Lincheng Jiang , Xieping Gao

Quantization effectively reduces the serving costs of Large Language Models (LLMs) by speeding up data movement through compressed parameters and enabling faster operations via integer arithmetic. However, activating integer arithmetic…

Machine Learning · Computer Science 2025-06-04 Patrik Czakó , Gábor Kertész , Sándor Szénási

Feature steering has emerged as a promising approach for controlling LLM behavior through direct manipulation of internal representations, offering advantages over prompt engineering. However, its practical effectiveness in real-world…

Steering vectors are a lightweight method to control language model behavior by adding a learned bias to the activations at inference time. Although steering demonstrates promising performance, recent work shows that it can be unreliable or…

Machine Learning · Computer Science 2025-05-29 Joschka Braun , Carsten Eickhoff , David Krueger , Seyed Ali Bahrainian , Dmitrii Krasheninnikov

Large language models (LLMs) exhibit persistent miscalibration, especially after instruction tuning and preference alignment. Modified training objectives can improve calibration, but retraining is expensive. Inference-time steering offers…

Machine Learning · Computer Science 2026-02-06 Miranda Muqing Miao , Young-Min Cho , Lyle Ungar

Large Language Models (LLMs) are widely deployed in real-world applications, yet their internal mechanisms remain difficult to interpret and control, limiting our ability to diagnose and correct undesirable behaviors. Mechanistic…

Generating stylized large language model (LLM) responses via representation editing is a promising way for fine-grained output control. However, there exists an inherent trade-off: imposing a distinctive style often degrades truthfulness.…

Computation and Language · Computer Science 2025-08-08 Chenglei Shen , Zhongxiang Sun , Teng Shi , Xiao Zhang , Jun Xu

Recent work has shown that LLMs can sometimes detect when steering vectors are injected into their residual stream and identify the injected concept -- a phenomenon termed "introspective awareness." We investigate the mechanisms underlying…

Machine Learning · Computer Science 2026-05-18 Uzay Macar , Li Yang , Atticus Wang , Peter Wallich , Emmanuel Ameisen , Jack Lindsey

Activation engineering enables precise control over Large Language Models (LLMs) without the computational cost of fine-tuning. However, existing methods deriving vectors from static activation differences are susceptible to…

Machine Learning · Computer Science 2026-03-16 Xinyan Jiang , Wenjing Yu , Di Wang , Lijie Hu

Reinforcement learning from human feedback (RLHF) typically assumes a static or non-strategic reward model (RM). In iterative deployment, however, the policy generates the data on which the RM is retrained, creating a feedback loop.…

Machine Learning · Computer Science 2026-05-07 Etienne Gauthier , Francis Bach , Michael I. Jordan

Large Language Models (LLMs) are vulnerable to adversarial attacks that bypass safety guidelines and generate harmful content. Mitigating these vulnerabilities requires defense mechanisms that are both robust and computationally efficient.…

Machine Learning · Computer Science 2025-11-18 Gil Goren , Shahar Katz , Lior Wolf

Accent variability remains a major errors in automatic speech recognition, yet most adaptation methods rely on parameter fine-tuning without understanding where accent information is encoded. We treat accent variation as an interpretable…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-09 Jinuo Sun , Yang Xiao , Sung Kyun Chung , Qiuchi Hu , Gongping Huang , Eun-Jung Holden , Ting Dang

Most jailbreak techniques for Large Language Models (LLMs) primarily rely on prompt modifications, including paraphrasing, obfuscation, or conversational strategies. Meanwhile, abliteration techniques (also known as targeted ablations of…

Cryptography and Security · Computer Science 2026-03-17 Maël Jenny , Jérémie Dentan , Sonia Vanier , Michaël Krajecki

Steering methods for language models (LMs) have gained traction as lightweight alternatives to fine-tuning, enabling targeted modifications to model activations. However, prior studies primarily report results on a few models, leaving…

Computation and Language · Computer Science 2025-04-08 Patrick Queiroz Da Silva , Hari Sethuraman , Dheeraj Rajagopal , Hannaneh Hajishirzi , Sachin Kumar

Large Language Models (LLMs) face persistent and evolving trustworthiness issues, motivating developers to seek automated and flexible repair methods that enable convenient deployment across diverse scenarios. Existing repair methods like…

Artificial Intelligence · Computer Science 2025-08-12 Changqing Li , Tianlin Li , Xiaohan Zhang , Aishan Liu , Li Pan

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