English
Related papers

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

200 papers

Large language models are increasingly used as planning components in agentic systems, but current tool-use pipelines often require full tool schemas to be included in every prompt, creating substantial token overhead and limiting the…

Computation and Language · Computer Science 2026-05-27 Yuval Shemla , Ayal Yakobe , Tanmay Agarwal , Dhaval Patel , Kaoutar El Maghraoui

This work examines whether activating latent subspaces in language models (LLMs) can steer scientific code generation toward a specific programming language. Five causal LLMs were first evaluated on scientific coding prompts to quantify…

Artificial Intelligence · Computer Science 2025-06-24 Vansh Sharma , Venkat Raman

Unlearning in large language models (LLMs) aims to remove harmful training data while preserving overall utility. However, we find that existing methods often hallucinate, generate abnormal token sequences, or behave inconsistently, raising…

Machine Learning · Computer Science 2026-05-12 Renjie Gu , Jiazhen Du , Yihua Zhang , Sijia Liu

Large language models (LLMs) can be dishonest when reporting on their actions and beliefs -- for example, they may overstate their confidence in factual claims or cover up evidence of covert actions. Such dishonesty may arise due to the…

Machine Learning · Computer Science 2025-12-24 Manas Joglekar , Jeremy Chen , Gabriel Wu , Jason Yosinski , Jasmine Wang , Boaz Barak , Amelia Glaese

Controlling the behavior of large language models (LLMs) at inference time is essential for aligning outputs with human abilities and safety requirements. \emph{Activation steering} provides a lightweight alternative to prompt engineering…

Artificial Intelligence · Computer Science 2026-01-30 Diaoulé Diallo , Katharina Dworatzyk , Sophie Jentzsch , Peer Schütt , Sabine Theis , Tobias Hecking

Inference-time LLM alignment methods, particularly activation steering, offer an alternative to fine-tuning by directly modifying activations during generation. Existing methods, however, often rely on non-anticipative interventions that…

Machine Learning · Computer Science 2026-04-22 Julian Skifstad , Xinyue Annie Yang , Glen Chou

A key challenge in AI alignment is guiding large language models (LLMs) to follow desired behaviors at test time. Activation steering, which modifies internal model activations during inference, offers a potential solution. However, prior…

Machine Learning · Computer Science 2025-03-04 Reza Bayat , Ali Rahimi-Kalahroudi , Mohammad Pezeshki , Sarath Chandar , Pascal Vincent

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

Large Audio-Language Models and Multi-Modal Large Language Models have demonstrated strong capabilities in tasks such as Audio Question Answering (AQA), Audio Captioning, and Automatic Speech Recognition (ASR). However, there is growing…

Sound · Computer Science 2025-10-16 Tsung-En Lin , Kuan-Yi Lee , Hung-Yi Lee

Large language models (LLMs) have pushed the limits of natural language understanding and exhibited excellent problem-solving ability. Despite the great success, most existing open-source LLMs (e.g., LLaMA-2) are still far away from…

Computation and Language · Computer Science 2024-05-06 Longhui Yu , Weisen Jiang , Han Shi , Jincheng Yu , Zhengying Liu , Yu Zhang , James T. Kwok , Zhenguo Li , Adrian Weller , Weiyang Liu

Diffusion-based large language models (dLLMs) are trained flexibly to model extreme dependence in the data distribution; however, how to best utilize this information at inference time remains an open problem. In this work, we uncover an…

Mixture-of-Experts (MoE) architectures in Large Language Models (LLMs) have significantly reduced inference costs through sparse activation. However, this sparse activation paradigm also introduces new safety challenges. Since only a subset…

Cryptography and Security · Computer Science 2026-05-01 Jona te Lintelo , Lichao Wu , Marina Krček , Sengim Karayalçin , Stjepan Picek

Large language models (LLMs) remain prone to factual inaccuracies and computational errors, including hallucinations and mistakes in mathematical reasoning. Recent work augmented LLMs with tools to mitigate these shortcomings, but often…

Computation and Language · Computer Science 2025-02-11 Ne Luo , Aryo Pradipta Gema , Xuanli He , Emile van Krieken , Pietro Lesci , Pasquale Minervini

Active learning methods for neural networks are usually based on greedy criteria which ultimately give a single new design point for the evaluation. Such an approach requires either some heuristics to sample a batch of design points at one…

Machine Learning · Computer Science 2020-01-28 Evgenii Tsymbalov , Sergei Makarychev , Alexander Shapeev , Maxim Panov

Multi-fidelity methods are prominently used when cheaply-obtained, but possibly biased and noisy, observations must be effectively combined with limited or expensive true data in order to construct reliable models. This arises in both…

Machine Learning · Statistics 2019-03-19 Kurt Cutajar , Mark Pullin , Andreas Damianou , Neil Lawrence , Javier González

In this paper, we explore the capacity of a language model-based method for grammatical error detection in detail. We first show that 5 to 10% of training data are enough for a BERT-based error detection method to achieve performance…

Computation and Language · Computer Science 2021-08-30 Ryo Nagata , Manabu Kimura , Kazuaki Hanawa

Discrete diffusion language models (DLMs) generate text by iteratively denoising all positions in parallel, offering an alternative to autoregressive models. Controlled generation methods for DLMs, imported from autoregressive models, apply…

Machine Learning · Computer Science 2026-05-13 Hanhan Zhou , Shamik Roy , Rashmi Gangadharaiah

Test-Time Scaling (TTS) methods for enhancing Large Language Model (LLM) reasoning often incur substantial computational costs, primarily due to extensive reliance on external Process Reward Models (PRMs) or sampling methods like Best-of-N…

Computation and Language · Computer Science 2025-05-28 Amirhosein Ghasemabadi , Keith G. Mills , Baochun Li , Di Niu

Adapting LLM agents to domain-specific tool calling remains notably brittle under evolving interfaces. Prompt and schema engineering is easy to deploy but often fragile under distribution shift and strict parsers, while continual…

Software Engineering · Computer Science 2026-02-10 Youjin Wang , Run Zhou , Rong Fu , Shuaishuai Cao , Hongwei Zeng , Jiaxuan Lu , Sicheng Fan , Jiaqiao Zhao , Liangming Pan

Neural network pruning has emerged as a promising approach for deploying LLMs in low-resource scenarios while preserving downstream task performance. However, for the first time, we reveal that such pruning disrupts LLMs' internal…

Machine Learning · Computer Science 2025-09-04 Yao Fu , Runchao Li , Xianxuan Long , Haotian Yu , Xiaotian Han , Yu Yin , Pan Li
‹ Prev 1 4 5 6 7 8 10 Next ›