In-context Continual Learning Assisted by an External Continual Learner

• URL: http://arxiv.org/abs/2412.15563v1
• Date: Fri, 20 Dec 2024 04:44:41 GMT
• Title: In-context Continual Learning Assisted by an External Continual Learner
• Abstract summary: Existing continual learning (CL) methods rely on fine-tuning or adapting large language models (LLMs)<n>We introduce InCA, a novel approach that integrates an external continual learner (ECL) with ICL to enable scalable CL without CF.
• Score: 19.382196203113836
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Existing continual learning (CL) methods mainly rely on fine-tuning or adapting large language models (LLMs). They still suffer from catastrophic forgetting (CF). Little work has been done to exploit in-context learning (ICL) to leverage the extensive knowledge within LLMs for CL without updating any parameters. However, incrementally learning each new task in ICL necessitates adding training examples from each class of the task to the prompt, which hampers scalability as the prompt length increases. This issue not only leads to excessively long prompts that exceed the input token limit of the underlying LLM but also degrades the model's performance due to the overextended context. To address this, we introduce InCA, a novel approach that integrates an external continual learner (ECL) with ICL to enable scalable CL without CF. The ECL is built incrementally to pre-select a small subset of likely classes for each test instance. By restricting the ICL prompt to only these selected classes, InCA prevents prompt lengths from becoming excessively long, while maintaining high performance. Experimental results demonstrate that InCA significantly outperforms existing CL baselines, achieving substantial performance gains.

Related papers

• A Practical Guide to Streaming Continual Learning [53.995807801604506]
  Continual Learning (CL) and Streaming Machine Learning () study the ability of agents to learn from a stream of non-stationary data.<n>Despite sharing some similarities, they address different and complementary challenges.<n>We discuss Streaming Continual Learning (SCL), an emerging paradigm providing a unifying solution to real-world problems.
  arXiv  Detail & Related papers  (2026-03-02T10:06:34Z)
• ACL: Aligned Contrastive Learning Improves BERT and Multi-exit BERT Fine-tuning [3.060720241524644]
  We introduce a novel underlineAligned underlineContrastive underlineLearning (ACL) framework.<n>ACL-Embed regards label embeddings as extra augmented samples with different labels and employs contrastive learning to align the label embeddings with its samples' representations.<n>To facilitate the optimization of ACL-Embed objective combined with the CE loss, we propose ACL-Grad, which will discard the ACL-Embed term if the two objectives are in conflict.
  arXiv  Detail & Related papers  (2026-02-03T14:08:07Z)
• Counting Hypothesis: Potential Mechanism of In-Context Learning [0.4583541422554718]
  In-Context Learning (ICL) indicates that large language models (LLMs) pretrained on a massive amount of data can learn specific tasks from input prompts' examples.<n>We propose 1the counting hypothesis' of ICL, which suggests that LLMs' encoding strategy may underlie ICL.
  arXiv  Detail & Related papers  (2026-02-02T05:57:33Z)
• CLA: Latent Alignment for Online Continual Self-Supervised Learning [53.52783900926569]
  We introduce Continual Latent Alignment (CLA), a novel SSL strategy for Online CL.<n>Our CLA is able to speed up the convergence of the training process in the online scenario, outperforming state-of-the-art approaches under the same computational budget.<n>We also discovered that using CLA as a pretraining protocol in the early stages of pretraining leads to a better final performance when compared to a full i.i.d. pretraining.
  arXiv  Detail & Related papers  (2025-07-14T16:23:39Z)
• Continual Learning Using Only Large Language Model Prompting [13.987306383667518]
  We introduce CLOB, a novel continual learning paradigm wherein a large language model (LLM) is regarded as a black box.<n>We also propose a new CL technique, called CIS, based on incremental summarization that also overcomes the LLM's input length limit.
  arXiv  Detail & Related papers  (2024-12-20T01:21:57Z)
• Self-Calibrated CLIP for Training-Free Open-Vocabulary Segmentation [19.749490092520006]
  Self-Calibrated CLIP (SC-CLIP) is a training-free method that calibrates CLIP to produce finer representations. SC-CLIP boosts the performance of vanilla CLIP ViT-L/14 by 6.8 times.
  arXiv  Detail & Related papers  (2024-11-24T15:14:05Z)
• ICLEval: Evaluating In-Context Learning Ability of Large Language Models [68.7494310749199]
  In-Context Learning (ICL) is a critical capability of Large Language Models (LLMs) as it empowers them to comprehend and reason across interconnected inputs.<n>Existing evaluation frameworks primarily focus on language abilities and knowledge, often overlooking the assessment of ICL ability.<n>We introduce the ICLEval benchmark to evaluate the ICL abilities of LLMs, which encompasses two key sub-abilities: exact copying and rule learning.
  arXiv  Detail & Related papers  (2024-06-21T08:06:10Z)
• Is In-Context Learning Sufficient for Instruction Following in LLMs? [38.29072578390376]
  We show that, while effective, ICL alignment withAL still underperforms compared to instruction fine-tuning on the established benchmark MT-Bench. We provide the first, to our knowledge, systematic comparison of ICL and instruction fine-tuning (IFT) for instruction following in the low data regime.
  arXiv  Detail & Related papers  (2024-05-30T09:28:56Z)
• Many-Shot In-Context Learning [58.395589302800566]
  Large language models (LLMs) excel at few-shot in-context learning (ICL) We observe significant performance gains across a wide variety of generative and discriminative tasks. Unlike few-shot learning, many-shot learning is effective at overriding pretraining biases.
  arXiv  Detail & Related papers  (2024-04-17T02:49:26Z)
• CLAP4CLIP: Continual Learning with Probabilistic Finetuning for Vision-Language Models [23.398619576886375]
  Continual learning (CL) aims to help deep neural networks learn new knowledge while retaining what has been learned. Our work proposes Continual LeArning with Probabilistic finetuning (CLAP) - a probabilistic modeling framework over visual-guided text features per task.
  arXiv  Detail & Related papers  (2024-03-28T04:15:58Z)
• Investigating the Learning Behaviour of In-context Learning: A Comparison with Supervised Learning [67.25698169440818]
  Large language models (LLMs) have shown remarkable capacity for in-context learning (ICL) We train the same LLMs with the same demonstration examples via ICL and supervised learning (SL), respectively, and investigate their performance under label perturbations. First, we find that gold labels have significant impacts on the downstream in-context performance, especially for large language models. Second, when comparing with SL, we show empirically that ICL is less sensitive to label perturbations than SL, and ICL gradually attains comparable performance to SL as the model size increases.
  arXiv  Detail & Related papers  (2023-07-28T09:03:19Z)
• On the Effectiveness of Equivariant Regularization for Robust Online Continual Learning [17.995662644298974]
  Continual Learning (CL) approaches seek to bridge this gap by facilitating the transfer of knowledge to both previous tasks and future ones. Recent research has shown that self-supervision can produce versatile models that can generalize well to diverse downstream tasks. We propose Continual Learning via Equivariant Regularization (CLER), an OCL approach that leverages equivariant tasks for self-supervision.
  arXiv  Detail & Related papers  (2023-05-05T16:10:31Z)
• OpenICL: An Open-Source Framework for In-context Learning [48.75452105457122]
  We introduce OpenICL, an open-source toolkit for In-context Learning (ICL) and large language model evaluation. OpenICL is research-friendly with a highly flexible architecture that users can easily combine different components to suit their needs. The effectiveness of OpenICL has been validated on a wide range of NLP tasks, including classification, QA, machine translation, and semantic parsing.
  arXiv  Detail & Related papers  (2023-03-06T06:20:25Z)
• Beyond Supervised Continual Learning: a Review [69.9674326582747]
  Continual Learning (CL) is a flavor of machine learning where the usual assumption of stationary data distribution is relaxed or omitted. Changes in the data distribution can cause the so-called catastrophic forgetting (CF) effect: an abrupt loss of previous knowledge. This article reviews literature that study CL in other settings, such as learning with reduced supervision, fully unsupervised learning, and reinforcement learning.
  arXiv  Detail & Related papers  (2022-08-30T14:44:41Z)
• Learning with Multiple Complementary Labels [94.8064553345801]
  A complementary label (CL) simply indicates an incorrect class of an example, but learning with CLs results in multi-class classifiers. We propose a novel problem setting to allow MCLs for each example and two ways for learning with MCLs.
  arXiv  Detail & Related papers  (2019-12-30T13:50:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.