English
Related papers

Related papers: Comparing Bottom-Up and Top-Down Steering Approach…

200 papers

Large language models (LLMs) exhibit impressive in-context learning (ICL) capability, enabling them to perform new tasks using only a few demonstrations in the prompt. Two different mechanisms have been proposed to explain ICL: induction…

Machine Learning · Computer Science 2025-05-05 Kayo Yin , Jacob Steinhardt

Demonstrations and instructions are two primary approaches for prompting language models to perform in-context learning (ICL) tasks. Do identical tasks elicited in different ways result in similar representations of the task? An improved…

Computation and Language · Computer Science 2025-12-02 Guy Davidson , Todd M. Gureckis , Brenden M. Lake , Adina Williams

Do large language models (LLMs) represent concepts abstractly, i.e., independent of input format? We revisit Function Vectors (FVs), compact representations of in-context learning (ICL) tasks that causally drive task performance. Across…

Computation and Language · Computer Science 2026-02-27 Gustaw Opiełka , Hannes Rosenbusch , Claire E. Stevenson

Large language models (LLMs) demonstrate emergent in-context learning capabilities, where they adapt to new tasks based on example demonstrations. However, in-context learning has seen limited effectiveness in many settings, is difficult to…

Machine Learning · Computer Science 2024-02-15 Sheng Liu , Haotian Ye , Lei Xing , James Zou

Steering vectors (SVs) offer a lightweight way to control large language models (LLMs) at inference time by shifting hidden activations, providing a practical middle ground between prompting and fine-tuning. Yet SVs can be unreliable in…

Computation and Language · Computer Science 2026-02-03 Jiaqian Li , Yanshu Li , Kuan-Hao Huang

This paper investigates how Large Language Models (LLMs) represent non-English tokens -- a question that remains underexplored despite recent progress. We propose a lightweight intervention method using representation steering, where a…

Computation and Language · Computer Science 2025-08-27 Omar Mahmoud , Buddhika Laknath Semage , Thommen George Karimpanal , Santu Rana

Steering methods have emerged as effective and targeted tools for guiding large language models' (LLMs) behavior without modifying their parameters. Multimodal large language models (MLLMs), however, do not currently enjoy the same suite of…

Machine Learning · Computer Science 2025-05-21 Woody Haosheng Gan , Deqing Fu , Julian Asilis , Ollie Liu , Dani Yogatama , Vatsal Sharan , Robin Jia , Willie Neiswanger

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

Applying steering vectors to large language models (LLMs) is an efficient and effective model alignment technique, but we lack an interpretable explanation for how it works-- specifically, what internal mechanisms steering vectors affect…

Machine Learning · Computer Science 2026-04-10 Stephen Cheng , Sarah Wiegreffe , Dinesh Manocha

We report the presence of a simple neural mechanism that represents an input-output function as a vector within autoregressive transformer language models (LMs). Using causal mediation analysis on a diverse range of in-context-learning…

Computation and Language · Computer Science 2024-02-27 Eric Todd , Millicent L. Li , Arnab Sen Sharma , Aaron Mueller , Byron C. Wallace , David Bau

State-of-the-art Vision-Language Models (VLMs) ground the vision and the language modality primarily via projecting the vision tokens from the encoder to language-like tokens, which are directly fed to the Large Language Model (LLM)…

Computer Vision and Pattern Recognition · Computer Science 2024-07-18 Sivan Doveh , Shaked Perek , M. Jehanzeb Mirza , Wei Lin , Amit Alfassy , Assaf Arbelle , Shimon Ullman , Leonid Karlinsky

Vision-Language Models (VLMs) have shown remarkable capabilities in a large number of downstream tasks. Nonetheless, compositional image understanding remains a rather difficult task due to the object bias present in training data. In this…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Matteo Nulli , Anesa Ibrahimi , Avik Pal , Hoshe Lee , Ivona Najdenkoska

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) can perform new tasks from in-context demonstrations, a phenomenon known as in-context learning (ICL). Recent work suggests that these demonstrations are compressed into task vectors (TVs), compact task…

Computation and Language · Computer Science 2026-05-04 Haolin Yang , Hakaze Cho , Kaize Ding , Naoya Inoue

The ability to follow instructions is crucial for numerous real-world applications of language models. In pursuit of deeper insights and more powerful capabilities, we derive instruction-specific vector representations from language models…

Computation and Language · Computer Science 2025-04-15 Alessandro Stolfo , Vidhisha Balachandran , Safoora Yousefi , Eric Horvitz , Besmira Nushi

Function vectors (FVs) are vector representations of tasks extracted from model activations during in-context learning. While prior work has shown that multilingual model representations can be language-agnostic, it remains unclear whether…

Computation and Language · Computer Science 2026-04-22 Nurkhan Laiyk , Gerard I. Gállego , Javier Ferrando , Fajri Koto

As language models continue to scale, Large Language Models (LLMs) have exhibited emerging capabilities in In-Context Learning (ICL), enabling them to solve language tasks by prefixing a few in-context demonstrations (ICDs) as context.…

Computation and Language · Computer Science 2024-11-01 Yingzhe Peng , Chenduo Hao , Xu Yang , Jiawei Peng , Xinting Hu , Xin Geng

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

Vision-and-Language Navigation (VLN) refers to the task of enabling autonomous robots to navigate unfamiliar environments by following natural language instructions. While recent Large Vision-Language Models (LVLMs) have shown promise in…

Computer Vision and Pattern Recognition · Computer Science 2025-08-06 Vebjørn Haug Kåsene , Pierre Lison

Steering vectors are a lightweight method for controlling language model behavior by adding a learned bias to the activations at inference time. Although effective on average, steering effect sizes vary across samples and are unreliable for…

Computation and Language · Computer Science 2026-02-23 Joschka Braun
‹ Prev 1 2 3 10 Next ›