AI Paper Atlas

Research map / Continual learning / Continual fine-tuning of LLMs

Understanding Generalization and Forgetting in In-Context Continual Learning

Guangyu Li, Meng Ding, Lijie Hu

ICML 2026 · Continual learning › Continual fine-tuning of LLMs · approach: Continual pretraining of language models · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
increase in-context examples M per task when earlier tasks are misaligned (ablation)GPT-2 on linear regression task sequences · synthetic linear regression, tasks 2-5normalized MSEMixed
increase context length M in single-task position (Task 1) (ablation)GPT-2 on linear regression · synthetic linear regression, Task 1prediction errorImproved
increase angle between task weight vectors (lower task similarity) (ablation)GPT-2 on linear regression sequences · synthetic linear regressionnormalized MSEHurt
place a similar task earlier in the prompt (cluster {1,3,5}) (ablation)GPT-2 on linear regression · synthetic linear regression, 5 tasksper-task MSEImproved
change task order in the prompt (ablation)GPT-2 on linear regression · synthetic linear regression, 6 permutationsmean forgettingMixed
increase M on sparse linear regression and two-layer ReLU tasks (ablation)GPT-2 · sparse linear regression, Task 5normalized MSE: 0.9905 at M = 19Hurt
prepend SST-2 examples before AG News examples (small M) (ablation)Qwen2.5-1.5B-Instruct · AG News accuracyaccuracy: 0.736 -> 0.580 (M=1)Hurt
increase M to 19 with prepended SST-2 context (ablation)Qwen2.5-1.5B-Instruct · AG News accuracyaccuracy: 0.668 -> 0.684 (M=19)No clear effect
append AG News examples after SST-2 examples, query SST-2 at end (ablation)Qwen2.5-1.5B-Instruct · SST-2 accuracyaccuracy: 0.934 -> 0.472 (M=1)Hurt
increase M from 1 to 19 for Task A retention (ablation)Qwen2.5-1.5B-Instruct · SST-2 accuracyaccuracy: 0.472 -> 0.536Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy