English
Related papers

Related papers: Depth-Wise Activation Steering for Honest Language…

200 papers

Large Language Models (LLMs) such as GPT, LLaMA, and Claude achieve remarkable performance in text generation but remain opaque in their decision-making processes, limiting trust and accountability in high-stakes applications. We present…

Computation and Language · Computer Science 2025-10-22 Zeinab Dehghani , Mohammed Naveed Akram , Koorosh Aslansefat , Adil Khan , Yiannis Papadopoulos

Explainable AI (XAI) methods reveal which features influence model predictions, yet provide limited means for practitioners to act on these explanations. Activation steering of components identified via XAI offers a path toward actionable…

Artificial Intelligence · Computer Science 2026-05-27 Tobias Labarta , Maximilian Dreyer , Katharina Weitz , Wojciech Samek , Sebastian Lapuschkin

Augmenting large language models (LLM) to use external tools enhances their performance across a variety of tasks. However, prior works over-rely on task-specific demonstration of tool use that limits their generalizability and…

Artificial Intelligence · Computer Science 2024-02-01 Yining Lu , Haoping Yu , Daniel Khashabi

The growing use of generative models in daily life calls for efficient mechanisms to control their generation, to e.g., produce safe content or provide users with tools to explore style changes. Ideally, such mechanisms should require low…

Computation and Language · Computer Science 2025-10-20 Pau Rodriguez , Michal Klein , Eleonora Gualdoni , Valentino Maiorca , Arno Blaas , Luca Zappella , Marco Cuturi , Xavier Suau

Steering vectors offer a training-free mechanism for controlling reasoning behaviors in large language models, but constructing effective vectors requires identifying genuine behavioral signals in the model's hidden states. For behaviors…

Computation and Language · Computer Science 2026-04-03 Haomin Zhuang , Hojun Yoo , Xiaonan Luo , Kehan Guo , Xiangliang Zhang

Language models have been shown to perform remarkably well on a wide range of natural language processing tasks. In this paper, we propose LEAP, a novel system that uses language models to perform multi-step logical reasoning and…

Computation and Language · Computer Science 2023-11-08 Hongyu Zhao , Kangrui Wang , Mo Yu , Hongyuan Mei

Scaling laws predict loss from compute but not how capabilities interact. We measure the coupling between reasoning and truthfulness across 63 base models from 16 families and find a regime change invisible to loss curves: below a…

Machine Learning · Computer Science 2026-05-26 Adil Amin

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

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

As Large Langue Models have been shown to memorize real-world facts, the need to update this knowledge in a controlled and efficient manner arises. Designed with these constraints in mind, Knowledge Editing (KE) approaches propose to alter…

Artificial Intelligence · Computer Science 2025-07-30 Marco Scialanga , Thibault Laugel , Vincent Grari , Marcin Detyniecki

Recent advancements in large reasoning models (LRMs) have significantly enhanced language models' capabilities in complex problem-solving by emulating human-like deliberative thinking. However, these models often exhibit overthinking (i.e.,…

Artificial Intelligence · Computer Science 2025-06-19 Weixiang Zhao , Jiahe Guo , Yang Deng , Xingyu Sui , Yulin Hu , Yanyan Zhao , Wanxiang Che , Bing Qin , Tat-Seng Chua , Ting Liu

Large Language Models (LLMs) have dramatically advanced AI applications, yet their deployment remains challenging due to their immense inference costs. Recent studies ameliorate the computational costs of LLMs by increasing their activation…

Machine Learning · Computer Science 2024-11-05 Donghyun Lee , Je-Yong Lee , Genghan Zhang , Mo Tiwari , Azalia Mirhoseini

Although recent quantized Large Language Models (LLMs), such as BitNet, have paved the way for significant reduction in memory usage during deployment with binary or ternary weights, training these models still demands substantial memory…

Machine Learning · Computer Science 2025-10-13 Kaiyan Zhao , Tsuguchika Tabaru , Kenichi Kobayashi , Takumi Honda , Masafumi Yamazaki , Yoshimasa Tsuruoka

Language models often achieve higher accuracy when reasoning step-by-step in complex tasks. However, even when arriving at a correct final answer, their rationales are often logically unsound or inconsistent. This is a major issue when…

Artificial Intelligence · Computer Science 2023-11-09 Gabriel Poesia , Kanishk Gandhi , Eric Zelikman , Noah D. Goodman

Discrete diffusion models offer global context awareness and flexible parallel generation. However, uniform random noise schedulers in standard DLLM training overlook the highly non-uniform information density inherent in real-world…

Machine Learning · Computer Science 2026-03-18 Linrui Ma , Yufei Cui , Kai Han , Yunhe Wang

Mathematical reasoning has been challenging for large language models (LLMs), and the introduction of step-by-step Chain-of-Thought (CoT) inference has significantly advanced the mathematical capabilities of LLMs. However, current…

Artificial Intelligence · Computer Science 2025-09-23 Lang Cao , Yingtian Zou , Chao Peng , Renhong Chen , Wu Ning , Yitong Li

Activation steering methods control large language model (LLM) behavior by modifying internal activations at inference time. However, most existing activation steering methods rely on a fixed steering strength, leading to either…

Computation and Language · Computer Science 2025-10-16 Arthur Vogels , Benjamin Wong , Yann Choho , Annabelle Blangero , Milan Bhan

Large Language Models have achieved remarkable success across various natural language processing tasks, yet their high computational cost during inference remains a major bottleneck. This paper introduces Sparse Expert Activation Pruning…

Computation and Language · Computer Science 2025-03-11 Xun Liang , Hanyu Wang , Huayi Lai , Simin Niu , Shichao Song , Jiawei Yang , Jihao Zhao , Feiyu Xiong , Bo Tang , Zhiyu Li

Fact-seeking question answering with large language models (LLMs) remains unreliable when answers depend on up-to-date or conflicting information. Although retrieval-augmented and tool-using LLMs reduce hallucinations, they often rely on…

Computation and Language · Computer Science 2026-03-17 Auksarapak Kietkajornrit , Jad Tarifi , Nima Asgharbeygi

The proliferation of time series foundation models has created a landscape where no single method achieves consistent superiority, framing the central challenge not as finding the best model, but as orchestrating an optimal ensemble with…

Artificial Intelligence · Computer Science 2025-12-19 Defu Cao , Michael Gee , Jinbo Liu , Hengxuan Wang , Wei Yang , Rui Wang , Yan Liu