English
Related papers

Related papers: ICL Optimized Fragility

200 papers

In this work, we explore the mechanism of in-context learning (ICL) on out-of-distribution (OOD) tasks that were not encountered during training. To achieve this, we conduct synthetic experiments where the objective is to learn OOD…

Machine Learning · Computer Science 2024-12-05 Qixun Wang , Yifei Wang , Yisen Wang , Xianghua Ying

Despite its success, existing in-context learning (ICL) relies on in-domain expert demonstrations, limiting its applicability when expert annotations are scarce. We posit that different domains may share underlying reasoning structures,…

Artificial Intelligence · Computer Science 2026-04-08 Le Liu , Zhiming Li , Jianzhi Yan , Zike Yuan , Shiwei Chen , Youcheng Pan , Buzhou Tang , Qingcai Chen , Yang Xiang , Danny Dongning Sun

While Chain-of-Thought (CoT) prompting empowers Large Language Models (LLMs), ensuring reasoning reliability remains an open challenge. Contrary to the prevailing cascading failure hypothesis which posits that early errors are most…

Computation and Language · Computer Science 2026-03-04 Dongxu Zhang , Yujun Wu , Yiding Sun , Jinnan Yang , Ning Yang , Jihua Zhu , Miao Xin , Baoliang Tian

Algorithms that balance the stability-plasticity trade-off are well studied in the Continual Learning literature. However, only a few focus on obtaining models for specified trade-off preferences. When solving the problem of continual…

Machine Learning · Computer Science 2025-10-15 Pengyuan Lu , Michele Caprio , Eric Eaton , Insup Lee

Large language models (LLMs) like transformers demonstrate impressive in-context learning (ICL) capabilities, allowing them to make predictions for new tasks based on prompt exemplars without parameter updates. While existing ICL theories…

Machine Learning · Computer Science 2024-11-12 Kevin Christian Wibisono , Yixin Wang

While multi-task learning (MTL) has gained significant attention in recent years, its underlying mechanisms remain poorly understood. Recent methods did not yield consistent performance improvements over single task learning (STL)…

Machine Learning · Computer Science 2024-08-16 Cathrin Elich , Lukas Kirchdorfer , Jan M. Köhler , Lukas Schott

In-context learning (ICL) achieves remarkable performance in various domains such as knowledge acquisition, commonsense reasoning, and semantic understanding. However, its performance significantly deteriorates for emotion detection tasks,…

Machine Learning · Computer Science 2025-10-13 Zhaochun Ren , Zhou Yang , Chenglong Ye , Yufeng Wang , Haizhou Sun , Chao Chen , Xiaofei Zhu , Yunbing Wu , Xiangwen Liao

In-context learning (ICL) of large language models has proven to be a surprisingly effective method of learning a new task from only a few demonstrative examples. In this paper, we study the efficacy of ICL from the viewpoint of statistical…

Machine Learning · Statistics 2024-10-03 Juno Kim , Tai Nakamaki , Taiji Suzuki

Code data has been shown to enhance the reasoning capabilities of large language models (LLMs), but it remains unclear which aspects of code are most responsible. We investigate this question with a systematic, data-centric framework. We…

Computation and Language · Computer Science 2025-10-03 Abdul Waheed , Zhen Wu , Carolyn Rosé , Daphne Ippolito

In-context learning (ICL) is an important paradigm for adapting large language models (LLMs) to new tasks, but the generalization behavior of ICL remains poorly understood. We investigate the inductive biases of ICL from the perspective of…

Computation and Language · Computer Science 2023-05-23 Chenglei Si , Dan Friedman , Nitish Joshi , Shi Feng , Danqi Chen , He He

Recent work has questioned whether large language models (LLMs) can perform genuine in-context learning (ICL) for scientific experimental design, with prior studies suggesting that LLM-based agents exhibit no sensitivity to experimental…

Large language models (LLMs) have demonstrated impressive performance on a number of natural language processing tasks, such as question answering and text summarization. However, their performance on sequence labeling tasks such as intent…

Computation and Language · Computer Science 2024-02-27 Yao Qiang , Subhrangshu Nandi , Ninareh Mehrabi , Greg Ver Steeg , Anoop Kumar , Anna Rumshisky , Aram Galstyan

Large language models (LLMs) such as GPT, Gemini, and Claude often appear adept at solving classic logic puzzles--but how much genuine reasoning underlies their answers? Recent evidence suggests that these models frequently rely on…

Computation and Language · Computer Science 2025-10-15 Souradeep Mukhopadhyay , Rishabh Baral , Nimeesh Mahajan , Samhitha Harish , Aswin RRV , Mihir Parmar , Mutsumi Nakamura , Chitta Baral

Large Language Models (LLMs) have demonstrated remarkable proficiency across diverse tasks, exhibiting emergent properties such as semantic prompt comprehension, In-Context Learning (ICL), and Chain-of-Thought (CoT) reasoning. Despite their…

Computation and Language · Computer Science 2026-03-13 Yuling Jiao , Yanming Lai , Huazhen Lin , Wensen Ma , Houduo Qi , Defeng Sun

Differentiable inductive logic programming (ILP) techniques have proven effective at finding approximate rule-based solutions to link prediction and node classification problems on knowledge graphs; however, the common assumption of…

Artificial Intelligence · Computer Science 2025-08-12 Blair Johnson , Clayton Kerce , Faramarz Fekri

In-context Learning (ICL) is the ability of Large Language Models (LLMs) to perform new tasks when conditioned on prompts comprising a few task examples. However, ICL performance can be critically sensitive to the choice of examples. To…

Computation and Language · Computer Science 2024-02-23 Shivanshu Gupta , Clemens Rosenbaum , Ethan R. Elenberg

Current approaches for strengthening LLM reasoning tend to introduce a training bias toward human-like reasoning trajectories. In step-wise preference optimization, in particular, dependence on human or higher-capacity model annotations for…

Computation and Language · Computer Science 2026-02-03 Junjie Lu , Yuliang Liu , Chaofeng Qu , Wei Shen , Zhouhan Lin , Chuheng Zhang , Min Xu

This paper investigates the expected excess risk of in-context learning (ICL) for multiclass classification. We formalize each task as a sequence of labeled examples followed by a query input; a pretrained model then estimates the query's…

Machine Learning · Statistics 2025-09-03 Chenrui Liu , Falong Tan , Chuanlong Xie , Yicheng Zeng , Lixing Zhu

Continual learning enables incremental learning of new tasks without forgetting those previously learned, resulting in positive knowledge transfer that can enhance performance on both new and old tasks. However, continual learning poses new…

Machine Learning · Computer Science 2023-08-01 Dawid Rymarczyk , Joost van de Weijer , Bartosz Zieliński , Bartłomiej Twardowski

Large language models demonstrate strong performance on mathematical reasoning benchmarks, yet remain surprisingly fragile to meaning-preserving surface perturbations. We systematically evaluate three open-weight LLMs, Mistral-7B,…

Computation and Language · Computer Science 2026-04-03 Shou-Tzu Han , Rodrigue Rizk , KC Santosh