AI Paper Atlas

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

Hessian-Enhanced Token Attribution (HETA): Interpreting Autoregressive LLMs

Vishal Pramanik, Maisha Maliha, Nathaniel D. Bastian, Sumit Kumar Jha

ICLR 2026 · Large language models › Language, safety and interpretability · approach: Parallel and early-exit decoding · 1 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
use HETA instead of ReAgent (next best) for attribution faithfulnessdecoder-only LMs · LongRA Soft-NC, GPT-J 6BSoft-NC: 1.68 -> 10.3Improved
use HETA instead of ReAgent on curated DSA alignmentdecoder-only LMs · Curated DSA, GPT-JDSA: 3.60 -> 4.80Improved
use HETA instead of baselines under decoding hyperparameter sweepLlama-3.1 70B · Soft-NC sensitivity to decoding settingsmax relative change (%): 2.3 -> 0.6Improved
remove semantic transition vector or replace with uniform weighting (ablation)HETA · LongRA, TellMeWhy, WikiBio, curated (GPT-J 6B)Soft-NC, Soft-NS, DSAImproved
add Hessian-based sensitivity and KL information terms to transition (ablation)HETA · LongRA, TellMeWhy, WikiBio, curated (GPT-J 6B)Soft-NC, Soft-NS, DSAImproved

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