AI Paper Atlas

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

Linguistic Properties and Model Scale in Brain Encoding: From Small to Compressed Language Models

SUBBA REDDY OOTA, Vijay Rowtula, Satya Sai Srinath Namburi GNVV, Khushbu Pahwa, Anant Khandelwal, Manish Gupta, Tanmoy Chakraborty, Bapi Raju Surampudi

ICML 2026 · Large language models › Language, safety and interpretability · approach: Linguistic encoding in LLM representations · 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
scale Qwen2.5 from 3B to 14B parameters (ablation)Qwen2.5 · whole-brain fMRI encoding, Moth Radio Hourbest-layer encoding score: 3B - 14B: 0.000 (p = 1.0)No clear effect
scale Qwen2.5 from 1.5B to 3B parameters (ablation)Qwen2.5 · whole-brain fMRI encodingbest-layer encoding score: +0.073 (p = 0.004)Improved
scale Qwen2.5 from 7B to 3B (ablation)Qwen2.5 · whole-brain fMRI encodingbest-layer encoding score: 3B - 7B: 0.028 (p = 0.06)Mixed
scale LLaMA-3.2 3B vs 1B in brain-to-text decoding (ablation)LLaMA-3.2 · brain-to-text decodingBLEU-1 / WER: BLEU-1 0.1105 -> 0.1198; WER 4.4869 -> 4.2237Improved
apply AWQ or SmoothQuant quantization to 3B SLM (ablation)Qwen2.5-3B · normalized brain alignmentnormalized brain alignment: 0.924 -> 0.933 (AWQ), 0.930 (SmoothQuant)No clear effect
apply GPTQ quantization to the model (ablation)Qwen2.5-3B / 7B · normalized brain alignmentnormalized brain alignment: 0.924 -> 0.910 (3B)Hurt
apply AWQ quantization to 7B model (ablation)Qwen2.5-7B · normalized brain alignmentbest-layer score: -0.020 (7B minus AWQ), p < 0.001Improved
apply 10-50% unstructured magnitude pruning to 3B model (ablation)Qwen2.5-3B · normalized brain alignmentnormalized brain alignment: 0.924 -> 0.910 / 0.908 / 0.907No clear effect
apply 50% pruning to 1.5B model (ablation)Qwen2.5-1.5B · normalized brain alignmentnormalized brain alignmentHurt
compress or shrink to 1-1.5B models (with or without quantization) (ablation)Qwen2.5 / LLaMA / DeepSeek · language-ROI normalized alignmentnormalized brain alignmentHurt
apply GPTQ to LLMs and 3B SLMs and probe linguistic tasks (ablation)quantized models · FlashHolmesdiscourse/reasoning/morphology probingHurt
compression degrading discourse, syntax and morphology probingcompressed LMs · brain alignment vs FlashHolmesnormalized brain alignmentNo clear effect

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