Using Captum to Explain Generative Language Models

Aobo Yang; Aram H. Markosyan; Diego Garcia-Olano; Narine Kokhlikyan; Vivek Miglani

Using Captum to Explain Generative Language Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2312.05491 v1 pith:M644GZU2 submitted 2023-12-09 cs.CL cs.AI

Vivek Miglani , Aobo Yang , Aram H. Markosyan , Diego Garcia-Olano , Narine Kokhlikyan This is my paper · ORCID

classification cs.CLcs.AI

keywords modelscaptumgenerativelanguagepytorchunderstandinganalyzeapplications

verification ladder T0 review T1 audit T2 compute T3 formal

0 comments

read the original abstract

Captum is a comprehensive library for model explainability in PyTorch, offering a range of methods from the interpretability literature to enhance users' understanding of PyTorch models. In this paper, we introduce new features in Captum that are specifically designed to analyze the behavior of generative language models. We provide an overview of the available functionalities and example applications of their potential for understanding learned associations within generative 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

LBR: Towards Mitigating Length Bias in Large Language Models for Recommendation
cs.IR 2026-07 accept novelty 6.5 of 10

LBR removes length bias in LLM recommenders via length-aware attention offsets and Trie-branching information-length normalization, improving accuracy and fairness with negligible cost.

Pith tools