English
Related papers

Related papers: Causality $\neq$ Invariance: Function and Concept …

200 papers

Analogical reasoning relies on conceptual abstractions, but it is unclear whether Large Language Models (LLMs) harbor such internal representations. We explore distilled representations from LLM activations and find that function vectors…

Computation and Language · Computer Science 2025-03-06 Gustaw Opiełka , Hannes Rosenbusch , Claire E. Stevenson

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

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

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

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

Large language models (LLMs) often map semantically related prompts to similar internal representations at specific layers, even when their surface forms differ widely. We show that this behavior can be explained through Iterated Function…

Computation and Language · Computer Science 2026-01-21 Sotirios Panagiotis Chytas , Vikas Singh

A key objective of interpretability research on large language models (LLMs) is to develop methods for robustly steering models toward desired behaviors. To this end, two distinct approaches to interpretability -- ``bottom-up" and…

Machine Learning · Computer Science 2024-11-12 Madeline Brumley , Joe Kwon , David Krueger , Dmitrii Krasheninnikov , Usman Anwar

Despite impressive performance on language modelling and complex reasoning tasks, Large Language Models (LLMs) fall short on the same tasks in uncommon settings or with distribution shifts, exhibiting a lack of generalisation ability. By…

Computation and Language · Computer Science 2024-09-11 Gaël Gendron , Bao Trung Nguyen , Alex Yuxuan Peng , Michael Witbrock , Gillian Dobbie

Large Language Models (LLMs) have demonstrated remarkable abilities, one of the most important being in-context learning (ICL). With ICL, LLMs can derive the underlying rule from a few demonstrations and provide answers that comply with the…

Computation and Language · Computer Science 2025-12-23 Bowen Zheng , Ming Ma , Zhongqiao Lin , Tianming Yang

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

Large language models (LLMs) have demonstrated remarkable proficiency in in-context learning (ICL), where models adapt to new tasks through example-based prompts without requiring parameter updates. However, understanding how tasks are…

Computation and Language · Computer Science 2025-11-11 Baturay Saglam , Xinyang Hu , Zhuoran Yang , Dionysis Kalogerias , Amin Karbasi

Large language models (LLMs) have shown remarkable in-context learning (ICL) capabilities on textual data. We explore whether these capabilities can be extended to continuous vectors from diverse domains, obtained from black-box pretrained…

Computation and Language · Computer Science 2025-02-21 Yufan Zhuang , Chandan Singh , Liyuan Liu , Jingbo Shang , Jianfeng Gao

Large language models (LLMs) have shown remarkable ability in various language tasks, especially with their emergent in-context learning capability. Extending LLMs to incorporate visual inputs, large vision-language models (LVLMs) have…

Machine Learning · Computer Science 2025-10-13 Aneesh Komanduri , Karuna Bhaila , Xintao Wu

Concepts play a pivotal role in various human cognitive functions, including learning, reasoning and communication. However, there is very little work on endowing machines with the ability to form and reason with concepts. In particular,…

Computation and Language · Computer Science 2023-11-06 Chen Shani , Jilles Vreeken , Dafna Shahaf

Recent advancements in Vision-Language (VL) research have sparked new benchmarks for complex visual reasoning, challenging models' advanced reasoning ability. Traditional Vision-Language Models (VLMs) perform well in visual perception tasks…

Computer Vision and Pattern Recognition · Computer Science 2024-09-24 Zhiyuan Li , Dongnan Liu , Chaoyi Zhang , Heng Wang , Tengfei Xue , Weidong Cai

In-context learning (ICL) excels at new tasks from minimal examples, yet we still lack a mechanistic explanation of how few-shot prompts shape a model's function vector (FV)--a causal activation direction that drives task behavior on the…

Machine Learning · Computer Science 2026-05-26 Entang Wang , Yiwei Wang , Aleksandra Bakalova , Michael Hahn

People acquire concepts through rich physical and social experiences and use them to understand and navigate the world. In contrast, large language models (LLMs), trained solely through next-token prediction on text, exhibit strikingly…

Computation and Language · Computer Science 2025-11-11 Ningyu Xu , Qi Zhang , Chao Du , Qiang Luo , Xipeng Qiu , Xuanjing Huang , Menghan Zhang

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

Autoregressive vision-language models (VLMs) can handle many tasks within a single model, yet the representations that enable this capability remain opaque. We find that VLMs align conceptually equivalent inputs into a shared task vector,…

Computer Vision and Pattern Recognition · Computer Science 2025-05-08 Grace Luo , Trevor Darrell , Amir Bar

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
‹ Prev 1 2 3 10 Next ›