AI Paper Atlas

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

Harnessing the Unseen: The Hidden Influence of Intrinsic Knowledge in Long-Context Language Models

Yu Fu, Haz Sameen Shahgir, Hui Liu, Xianfeng Tang, Qi He, Yue Dong

AAAI 2026 · Large language models › Language, safety and interpretability · approach: Controlled text generation

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
make the question require parametric recall before retrieval (Hybrid NIAH) instead of standard NIAH (ablation)Llama-3.1-8B-Instruct · NIAH vs Hybrid NIAH (gen length 32, 3 random facts)average accuracy: 98.83 -> 67.47Hurt
add 0 to 3 random fact distractors to Hybrid NIAH (ablation)Llama-3.1-70B-Instruct · Hybrid NIAH (gen length 32)average accuracy: 95.73 -> 71.81Hurt
add 0 to 3 random fact distractors to standard NIAH (ablation)Qwen2.5-7B-Instruct · NIAH (gen length 32)average accuracy: 99.78 -> 99.92No clear effect
scale Llama-3.1 from 8B to 70BLlama-3.1 · Hybrid NIAH (gen length 32, 3 random facts)average accuracy: 67.47 -> 71.81No clear effect
scale Qwen2.5 from 7B to 72BQwen2.5 · Hybrid NIAH (gen length 32, 3 random facts)average accuracy: 73.14 -> 97.77Improved
increase generation length from 32 to 64 (ablation)Qwen2.5-72B-Instruct · Hybrid NIAH (0 random facts)average accuracy: 64.01 -> 94.16Improved
limit Qwen2.5-7B-Instruct-1M max input to 128k (ablation)Qwen2.5-7B-Instruct-1M · Hybrid NIAH (gen length 32, 3 random facts)average accuracy: 42.91 -> 79.31Improved
replace RoPE with STRING position remappingLlama-3.1-8B-Instruct and Mistral-7B-Instruct-v0.2 · HotpotQA-Context subsetaccuracyImproved
replace RoPE with STRING position remappingLlama-3.1-8B-Instruct and Mistral-7B-Instruct-v0.2 · HotpotQA-Parametric subset and I-WhoQA-IrrelevantaccuracyHurt
context that conflicts with parametric knowledge instead of aligning, at longer context lengthsLlama-3.1-8B-Instruct · I-WhoQAaccuracy gap: gap up to 10 pointsHurt

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