← Back to archive day

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

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

36

Recommendation Score

breakthrough🔴 AdvancedNLPAlignment & SafetyBenchmarkUseful for both

Research context

Primary field

NLP

Language understanding, generation, extraction, and evaluation.

Topics

Alignment & Safety

Paper type

Benchmark

Best for

Useful for both

arXiv categories

cs.CLcs.AIcs.CL

Why It Matters

HETA introduces the first Hessian-based attribution method for autoregressive LLMs, capturing non-linear causal dependencies in token generation—essential for building reliable, interpretable generative systems in production.

Abstract

Attribution methods seek to explain language model predictions by quantifying the contribution of input tokens to generated outputs. However, most existing techniques are designed for encoder-based architectures and rely on linear approximations that fail to capture the causal and semantic complexities of autoregressive generation in decoder-only models. To address these limitations, we propose Hessian-Enhanced Token Attribution (HETA), a novel attribution framework tailored for decoder-only language models. HETA combines three complementary components: a semantic transition vector that captures token-to-token influence across layers, Hessian-based sensitivity scores that model second-order effects, and KL divergence to measure information loss when tokens are masked. This unified design produces context-aware, causally faithful, and semantically grounded attributions. Additionally, we introduce a curated benchmark dataset for systematically evaluating attribution quality in generative settings. Empirical evaluations across multiple models and datasets demonstrate that HETA consistently outperforms existing methods in attribution faithfulness and alignment with human annotations, establishing a new standard for interpretability in autoregressive language models.

Published April 14, 2026
© 2026 A2A.pub — AI to Action. From papers to practice, daily.
Summaries are AI-assistedPrivacyTerms