English
Related papers

Related papers: Steer2Edit: From Activation Steering to Component-…

200 papers

Large Language Models (LLMs) exhibit impressive performance across diverse domains but often suffer from overconfidence, limiting their reliability in critical applications. We propose SteerConf, a novel framework that systematically steers…

Computation and Language · Computer Science 2025-05-27 Ziang Zhou , Tianyuan Jin , Jieming Shi , Qing Li

Large language model (LLM) steering has emerged as a promising paradigm for controlling model behavior at inference time through targeted manipulation of hidden states, offering a lightweight alternative to expensive retraining. However,…

Computation and Language · Computer Science 2026-03-03 Haolei Xu , Xinyu Mei , Yuchen Yan , Rui Zhou , Wenqi Zhang , Weiming Lu , Yueting Zhuang , Yongliang Shen

Latent steering exploits internal representations of Large Language Models (LLMs) to guide generation, yet interventions on dense states can entangle distinct semantic features. In this paper, we investigate attention query activations as a…

Machine Learning · Computer Science 2026-05-25 Sumanta Bhattacharyya , Pedram Rooshenas

The field of mechanistic interpretability in pre-trained transformer models has demonstrated substantial evidence supporting the ''linear representation hypothesis'', which is the idea that high level concepts are encoded as vectors in the…

Machine Learning · Computer Science 2025-10-08 Damjan Kalajdzievski

Large language models (LLMs) increasingly serve as automated evaluators, yet they suffer from "self-preference bias": a tendency to favor their own outputs over those of other models. This bias undermines fairness and reliability in…

Computation and Language · Computer Science 2025-09-05 Dani Roytburg , Matthew Bozoukov , Matthew Nguyen , Jou Barzdukas , Simon Fu , Narmeen Oozeer

Speculative decoding accelerates language model inference by separating generation into fast drafting and parallel verification. Its main limitation is drafter-verifier misalignment, which limits token acceptance and reduces overall…

Machine Learning · Computer Science 2025-11-14 Frédéric Berdoz , Peer Rheinboldt , Roger Wattenhofer

Instruction tuning has emerged as a critical paradigm for improving the capabilities and alignment of large language models (LLMs). However, existing iterative model-aware data selection methods incur significant computational overhead, as…

Machine Learning · Computer Science 2025-05-13 Xiaotian Lin , Yanlin Qi , Yizhang Zhu , Themis Palpanas , Chengliang Chai , Nan Tang , Yuyu Luo

Existing text-driven 3D human motion editing methods have demonstrated significant progress, but are still difficult to precisely control over detailed, part-specific motions due to their global modeling nature. In this paper, we propose…

Graphics · Computer Science 2026-01-01 Yujie Yang , Zhichao Zhang , Jiazhou Chen , Zichao Wu

With the growing complexity and capability of large language models, a need to understand model reasoning has emerged, often motivated by an underlying goal of controlling and aligning models. While numerous interpretability and steering…

Machine Learning · Computer Science 2025-02-12 Usha Bhalla , Suraj Srinivas , Asma Ghandeharioun , Himabindu Lakkaraju

Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, but controlling their behavior reliably remains challenging, especially in open-ended generation settings. This paper…

Computation and Language · Computer Science 2025-12-08 Zirui He , Mingyu Jin , Bo Shen , Ali Payani , Yongfeng Zhang , Mengnan Du

A variety of recent methods guide large language model outputs via the inference-time addition of steering vectors to residual-stream or attention-head representations. In contrast, we propose to inject steering vectors directly into the…

Machine Learning · Computer Science 2025-09-23 Max Torop , Aria Masoomi , Masih Eskandar , Jennifer Dy

Language model alignment has become an important component of AI safety, allowing safe interactions between humans and language models, by enhancing desired behaviors and inhibiting undesired ones. It is often done by tuning the model or…

Computation and Language · Computer Science 2025-05-28 Yotam Wolf , Noam Wies , Dorin Shteyman , Binyamin Rothberg , Yoav Levine , Amnon Shashua

Large Language Models (LLMs) have recently revolutionized the NLP field, while they still fall short in some specific down-stream tasks. In the work, we focus on utilizing LLMs to perform machine translation, where we observe that two…

Computation and Language · Computer Science 2024-10-10 Weichuan Wang , Zhaoyi Li , Defu Lian , Chen Ma , Linqi Song , Ying Wei

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) increasingly exhibit behaviors suggesting awareness of their evaluation context, often adapting their reasoning strategies in benchmark settings. Prior work has shown that such evaluation awareness can distort…

Computation and Language · Computer Science 2026-05-12 Yanshi Li , Xueru Bai , Shuman Liu , Haibo Zhang , Anxiang Zeng

Large Language Models (LLMs) are increasingly deployed for clinical reasoning tasks, which inherently require eliciting calibrated probabilistic beliefs based on available evidence. However, real-world clinical data are frequently…

Artificial Intelligence · Computer Science 2026-03-19 Yuta Kobayashi , Vincent Jeanselme , Shalmali Joshi

Understanding and controlling the behavior of large language models (LLMs) is an increasingly important topic in multilingual NLP. Beyond prompting or fine-tuning, , i.e.,~manipulating internal representations during inference, has emerged…

With the rapid advancement of large language models (LLMs), their deployment in real-world applications has become increasingly widespread. LLMs are expected to deliver robust performance across diverse tasks, user preferences, and…

Computation and Language · Computer Science 2025-11-21 Wei Xia , Zhi-Hong Deng

Test-time compute has emerged as a key paradigm for enhancing LLM reasoning, yet prevailing approaches like Best-of-N and majority voting apply uniform depth across inputs, wasting computation on simple queries while potentially…

Artificial Intelligence · Computer Science 2025-09-30 Yixin He , Lumingyuan Tang

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
‹ Prev 1 8 9 10 Next ›