English
Related papers

Related papers: Activation Patching for Interpretable Steering in …

200 papers

Deploying LLMs in real-world applications requires controllable output that satisfies multiple desiderata at the same time. While existing work extensively addresses LLM steering for a single behavior, \textit{compositional steering} --…

Computation and Language · Computer Science 2026-04-21 Gorjan Radevski , Kiril Gashteovski , Giwon Hong , Carolin Lawrence , Goran Glavaš

Changing the behavior of large language models (LLMs) can be as straightforward as editing the Transformer's residual streams using appropriately constructed "steering vectors." These modifications to internal neural activations, a form of…

Computation and Language · Computer Science 2025-05-20 Jian-Qiao Zhu , Haijiang Yan , Thomas L. Griffiths

Latent space steering methods provide a practical approach to controlling large language models by applying steering vectors to intermediate activations, guiding outputs toward desired behaviors while avoiding retraining. Despite their…

Machine Learning · Computer Science 2026-01-13 Shawn Im , Sharon Li

As large language models (LLMs) become more integrated into societal systems, the risk of them perpetuating and amplifying harmful biases becomes a critical safety concern. Traditional methods for mitigating bias often rely on data…

Artificial Intelligence · Computer Science 2025-08-13 Shivam Dubey

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

The ability to automatically generate music that appropriately matches an arbitrary input track is a challenging task. We present a novel controllable system for generating single stems to accompany musical mixes of arbitrary length. At the…

Sound · Computer Science 2024-02-05 Marco Pasini , Maarten Grachten , Stefan Lattner

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

Recent approaches in music generation rely on disentangled representations, often labeled as structure and timbre or local and global, to enable controllable synthesis. Yet the underlying properties of these embeddings remain underexplored.…

Activation steering methods were shown to be effective in conditioning language model generation by additively intervening over models' intermediate representations. However, the evaluation of these techniques has so far been limited to…

Computation and Language · Computer Science 2024-12-02 Daniel Scalena , Gabriele Sarti , Malvina Nissim

Steering vectors are a promising approach to aligning language model behavior at inference time. In this paper, we propose a framework to assess the limitations of steering vectors as alignment mechanisms. Using a framework of transformer…

Computation and Language · Computer Science 2025-05-05 Chebrolu Niranjan , Kokil Jaidka , Gerard Christopher Yeo

Recent advances in large language models (LLMs) have led to the development of thinking language models that generate extensive internal reasoning chains before producing responses. While these models achieve improved performance,…

Machine Learning · Computer Science 2025-10-23 Constantin Venhoff , Iván Arcuschin , Philip Torr , Arthur Conmy , Neel Nanda

Language models (LMs) automatically learn word embeddings during pre-training on language corpora. Although word embeddings are usually interpreted as feature vectors for individual words, their roles in language model generation remain…

Computation and Language · Computer Science 2024-06-07 Chi Han , Jialiang Xu , Manling Li , Yi Fung , Chenkai Sun , Nan Jiang , Tarek Abdelzaher , Heng Ji

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

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

We address the problem of accurately interpolating measured anechoic steering vectors with a deep learning framework called the neural field. This task plays a pivotal role in reducing the resource-intensive measurements required for…

Audio and Speech Processing · Electrical Eng. & Systems 2024-03-04 Diego Di Carlo , Aditya Arie Nugraha , Mathieu Fontaine , Mathieu Fontaine , Kazuyoshi Yoshii

While deep generative models have become the leading methods for algorithmic composition, it remains a challenging problem to control the generation process because the latent variables of most deep-learning models lack good…

Sound · Computer Science 2020-08-18 Ziyu Wang , Dingsu Wang , Yixiao Zhang , Gus Xia

Activation engineering is becoming increasingly popular as a means of online control of large language models (LLMs). In this work, we extend the idea of inference-time steering with vectors that represent a behavioral direction of interest…

Machine Learning · Computer Science 2024-11-26 Christopher M. Ackerman

Applications of deep learning for audio effects often focus on modeling analog effects or learning to control effects to emulate a trained audio engineer. However, deep learning approaches also have the potential to expand creativity…

Audio and Speech Processing · Electrical Eng. & Systems 2021-12-07 Christian J. Steinmetz , Joshua D. Reiss

Zero-shot Text-to-Speech (TTS) models can generate speech that captures both the voice timbre and accent of a reference speaker. However, disentangling these attributes remains challenging, as the output often inherits both the accent and…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-09 Mu Yang , John H. L. Hansen

Transformer-based models generate hidden states that are difficult to interpret. In this work, we analyze hidden states and modify them at inference, with a focus on motion forecasting. We use linear probing to analyze whether interpretable…

Machine Learning · Computer Science 2025-05-19 Omer Sahin Tas , Royden Wagner