Pith. sign in

REVIEW 1 cited by

Sequential Integrated Gradients: a simple but effective method for explaining language models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2305.15853 v1 pith:KSTIWJP7 submitted 2023-05-25 cs.CL cs.AIcs.LG

classification cs.CLcs.AIcs.LG
keywords modelslanguagebaselinegradientsintegratedmeaningmethodmethods
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Several explanation methods such as Integrated Gradients (IG) can be characterised as path-based methods, as they rely on a straight line between the data and an uninformative baseline. However, when applied to language models, these methods produce a path for each word of a sentence simultaneously, which could lead to creating sentences from interpolated words either having no clear meaning, or having a significantly different meaning compared to the original sentence. In order to keep the meaning of these sentences as close as possible to the original one, we propose Sequential Integrated Gradients (SIG), which computes the importance of each word in a sentence by keeping fixed every other words, only creating interpolations between the baseline and the word of interest. Moreover, inspired by the training procedure of several language models, we also propose to replace the baseline token "pad" with the trained token "mask". While being a simple improvement over the original IG method, we show on various models and datasets that SIG proves to be a very effective method for explaining language models.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. From Heuristic Selection to Automated Algorithm Design: LLMs Benefit from Strong Priors

    cs.LG 2026-03 conditional novelty 4.0 of 10

    Prompting LLMs with strong benchmark algorithm code, rather than relying on linguistic instructions, improves LLM-driven black-box optimization; the proposed BAG method outperforms five baselines on pbo and bbob.

Pith tools