English
Related papers

Related papers: IA2: Alignment with ICL Activations Improves Super…

200 papers

Language models have the ability to perform in-context learning (ICL), allowing them to flexibly adapt their behavior based on context. This contrasts with in-weights learning (IWL), where memorized information is encoded in model…

Computation and Language · Computer Science 2025-03-04 Suraj Anand , Michael A. Lepori , Jack Merullo , Ellie Pavlick

We study the question: How can we select the right data for fine-tuning to a specific task? We call this data selection problem active fine-tuning and show that it is an instance of transductive active learning, a novel generalization of…

Machine Learning · Computer Science 2024-06-24 Jonas Hübotter , Bhavya Sukhija , Lenart Treven , Yarden As , Andreas Krause

Instruction Fine-Tuning enhances pre-trained language models from basic next-word prediction to complex instruction-following. However, existing One-off Instruction Fine-Tuning (One-off IFT) method, applied on a diverse instruction, may not…

Computation and Language · Computer Science 2024-06-18 Wei Pang , Chuan Zhou , Xiao-Hua Zhou , Xiaojie Wang

As model context lengths continue to increase, the number of demonstrations that can be provided in-context approaches the size of entire training datasets. We study the behavior of in-context learning (ICL) at this extreme scale on…

Computation and Language · Computer Science 2025-03-05 Amanda Bertsch , Maor Ivgi , Emily Xiao , Uri Alon , Jonathan Berant , Matthew R. Gormley , Graham Neubig

Prior research shows that large language models (LLMs) exhibit systematic extrapolation bias when forming predictions from both experimental and real-world data, and that prompt-based approaches appear limited in alleviating this bias. We…

General Finance · Quantitative Finance 2026-05-05 Zhenyu Gao , Wenxi Jiang , Yutong Yan

In-context learning (ICL) enables large language models (LLMs) to adapt to new tasks without weight updates by learning from demonstration sequences. While ICL shows strong empirical performance, its internal representational mechanisms are…

Computation and Language · Computer Science 2025-10-07 Jiachen Jiang , Yuxin Dong , Jinxin Zhou , Zhihui Zhu

While large language models based on the transformer architecture have demonstrated remarkable in-context learning (ICL) capabilities, understandings of such capabilities are still in an early stage, where existing theory and mechanistic…

Machine Learning · Computer Science 2023-10-17 Tianyu Guo , Wei Hu , Song Mei , Huan Wang , Caiming Xiong , Silvio Savarese , Yu Bai

Sequence models have demonstrated the ability to perform tasks like channel equalization and symbol detection by automatically adapting to current channel conditions. This is done without requiring any explicit optimization and by…

Signal Processing · Electrical Eng. & Systems 2024-11-01 Zihang Song , Matteo Zecchin , Bipin Rajendran , Osvaldo Simeone

In recent years, large language models (LLMs) have demonstrated significant potential in complex reasoning tasks like mathematical problem-solving. However, existing research predominantly relies on reinforcement learning (RL) frameworks…

Machine Learning · Computer Science 2026-01-12 ShaoZhen Liu , Xinting Huang , Houwen Peng , Xin Chen , Xinyang Song , Qi Li , Zhenan Sun

While large language models (LLMs) exhibit strong reasoning abilities, their performance on complex tasks is often constrained by the limitations of their internal knowledge. A compelling approach to overcome this challenge is to augment…

Artificial Intelligence · Computer Science 2026-03-10 Yaoqi Ye , Yiran Zhao , Keyu Duan , Zeyu Zheng , Kenji Kawaguchi , Cihang Xie , Michael Qizhe Shieh

Supervised Fine-Tuning (SFT) is a critical step for enhancing the instruction-following capabilities of Large Language Models (LLMs) and adapting them to specialized domains. However, SFT often leads to a degradation of the model's general…

Computation and Language · Computer Science 2025-07-01 Fei Ding , Baiqiao Wang

Parameter-efficient fine-tuning (PEFT) allows model builders to capture the task-specific parameters into adapters, which are a fraction of the size of the original base model. Popularity of PEFT technique for fine-tuning has led to the…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-10-24 Saransh Gupta , Umesh Deshpande , Travis Janssen , Swami Sundararaman

Large language models exhibit exciting capabilities, yet can show surprisingly narrow generalization from finetuning. E.g. they can fail to generalize to simple reversals of relations they are trained on, or fail to make simple logical…

Transformer-based language models excel at in-context learning (ICL), where they can adapt to new tasks based on contextual examples, without parameter updates. In a specific form of ICL, which we refer to as \textit{contextual recall},…

Machine Learning · Computer Science 2026-03-24 Bhavya Vasudeva , Puneesh Deora , Alberto Bietti , Vatsal Sharan , Christos Thrampoulidis

Fine-tuning pretrained language models (LMs) without making any architectural changes has become a norm for learning various language downstream tasks. However, for non-language downstream tasks, a common practice is to employ task-specific…

In-Context Learning (ICL) is an important paradigm for adapting Large Language Models (LLMs) to downstream tasks through a few demonstrations. Despite the great success of ICL, the limitation of the demonstration number may lead to…

Computation and Language · Computer Science 2024-01-10 Caoyun Fan , Jidong Tian , Yitian Li , Hao He , Yaohui Jin

Large language models (LLMs) have achieved remarkable progress, with post-training playing a crucial role in enhancing their reasoning capabilities. Among post-training paradigms, supervised fine-tuning (SFT) is widely used: it leverages…

Computation and Language · Computer Science 2026-05-27 Lisong Sun , Li Wang , Chen Zhang , Jinyang Wu , Kui Zhang , Tianhao Peng , Wenjun Wu

In the domain of large language models (LLMs), arXiv:2305.16938 showed that few-shot full-model fine-tuning -- namely Vanilla Fine Tuning (FT) and Pattern-Based Fine Tuning (PBFT) --, and In-Context Learning (ICL) generalize similarly on…

Computation and Language · Computer Science 2024-05-24 Krishna Prasad Varadarajan Srinivasan , Prasanth Gumpena , Madhusudhana Yattapu , Vishal H. Brahmbhatt

With the rapid development of large language models (LLMs), an increasing number of applications leverage cloud-based LLM APIs to reduce usage costs. However, since cloud-based models' parameters and gradients are agnostic, users have to…

Machine Learning · Computer Science 2026-02-23 Hui Ma , Shaoyu Dou , Ya Liu , Fei Xing , Li Feng , Feng Pi

If a model has some behavioral tendency, such as sycophancy or misalignment, and it is trained on its own outputs, will the tendency be amplified in the next generation of models? We study this question by training a series of models where…

Artificial Intelligence · Computer Science 2026-05-05 Zephaniah Roe , Jack Sanderson , Dang Nguyen , Julian Huang , Todd Nief , Aryan Shrivastava , Chenhao Tan , Ari Holtzman