AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Revisiting Long-context Modeling from Context Denoising Perspective

Zecheng Tang, Baibei Ji, Juntao Li, Lijun Wu, Haijia Gui, Min Zhang

ICLR 2026 · Large language models › Language, safety and interpretability · approach: LLM unlearning and benchmarks

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
add context denoising training (CDT) on top of SFT for long-context alignmentLlama-3.1-8B-Instruct · LongBench-Eaverage score: 48.61 -> 50.92Improved
replace plain SFT with CDT (ablation)Llama-3.1-8B-Instruct · LongBench-Eaverage score: 48.72 -> 50.92Improved
use CDT instead of LongCE for context window scaling (ablation)Llama-3-8B-Base (8K to 64K) · LongBench-Eaverage score: 34.62 -> 39.31Improved
use LongCE or CE objective for post-training on base model (ablation)Llama-3.1-8B-Base · LongBench-Eaverage score: 37.13 -> 36.90 (LongCE); 37.13 -> 37.55 (CE)No clear effect
add CDT to post-training of base modelLlama-3.1-8B-Base · LongBench-Eaverage score: 37.13 -> 38.89Improved
add CDTLlama-3.1-8B-Instruct · RULER 128Kaverage score: 76.71 -> 78.72Improved
add CDTLlama-3.1-8B-Instruct · GovReport LongPPLLongPPL: 4.05 -> 2.36Improved
add CDTLlama-3.1-8B-Instruct · GovReport PPLPPL: 5.52 -> 5.64Hurt
add CDTLlama-3.1-8B-Instruct · BABILong avgaccuracy: 40.67 -> 43.30Improved
add CDTLlama-3.1-8B-Instruct / Qwen3-8B / Mistral-V0.3 · LongBench-Eaverage score: Qwen3-8B 38.85 -> 41.11; Mistral 44.06 -> 47.58Improved
add CDTMeta-Llama-3.1-8B · HELMETaverage score: 46.5 -> 49.7Improved
use embedding-gradient detection (CDT) instead of attention-based or LongPPL detection of critical tokens (ablation)CDT critical token detection · synthetic long-form reasoning taskcritical token detectionImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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