AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models

Baolong Bi, Shenghua Liu, Yiwei Wang, Yilong Xu, Junfeng Fang, Lingrui Mei, Xueqi Cheng

ICLR 2026 · Large language models › Retrieval and knowledge · approach: RAG robustness and evaluation · 43 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
add Confidence-Gain-based conflict detection before modulating tokens (ablation)CK-PLUG · NQ counterfactual context (alpha=0.0, LLaMA2-7B-chat)hit rate (%): 30.7 -> 74.8Improved
add conflict detection (ConD) (ablation)CK-PLUG · NQ counterfactual context (alpha=1.0, Qwen-instruct)hit rate (%): 51.3 -> 87.2Improved
add conflict detection (ConD) at moderate alpha (ablation)CK-PLUG · NQ counterfactual context (alpha=0.5, Mistral-instruct)hit rate (%): 91.3 -> 92.4No clear effect
set alpha from 0.0 to 1.0 to shift reliance toward parametric knowledge (ablation)CK-PLUG · NQ counterfactual context (LLaMA3-8B-instruct)MR (%): 9.9 -> 71.9Improved
alpha=0.5 as a neutral setting (ablation)CK-PLUG · NQ counterfactual context (LLaMA3-8B-instruct)MR (%): 43.5 -> 42.1No clear effect
use adaptive alpha from entropy ratio in general RAGRAG with LLaMA3-8B-instruct · HotpotQAaccuracy: 43.1 -> 46.7Improved
use adaptive alpha from entropy ratio in general RAGRAG with LLaMA2-7B-chat · FEVERaccuracy: 66.2 -> 72.6Improved
use adaptive alpha from entropy ratio in general RAGRAG with Qwen2.5-7B-instruct · T-REXaccuracy: 61.6 -> 60.2Hurt
use adaptive alpha from entropy ratio in general RAGRAG with LLaMA3-8B-instruct · FEVERaccuracy: 86.4 -> 86.1No clear effect
use adaptive alpha from entropy ratio in general RAGRAG with LLaMA2-7B-chat · ELI5 (Rouge-L)Rouge-L: 13.3 -> 14.1Improved

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