Skip to content
AI News HubLIVE
Original source2 min read

A Removal Based Approach to Improve LLM Faithfulness at Test-Time

Summary

This paper introduces a model-agnostic test-time method to improve the faithfulness of LLM explanations. It targets incompleteness by removing from the input concepts not credited in the model's explanation and re-querying the model. The authors show this improves explanation faithfulness across two datasets, multiple model families, and two independent metrics compared to standard prompting and prompting that encourages faithfulness.

SourcearXiv AIAuthor: Qinglan Luo, S M A Nahian, John Guttag, S. Mazdak Abulnaga, Katie Matton
A Removal Based Approach to Improve LLM Faithfulness at Test-Time
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 3 Sep 2026]

Title:A Removal Based Approach to Improve LLM Faithfulness at Test-Time

View a PDF of the paper titled A Removal Based Approach to Improve LLM Faithfulness at Test-Time, by Qinglan Luo and S M A Nahian and John Guttag and S. Mazdak Abulnaga and Katie Matton

View PDF HTML (experimental)

Abstract:Large language models (LLMs) are increasingly used for consequential decisions, making their explanations an important tool for auditing model behavior. Unfortunately, these explanations can be unfaithful, failing to reflect the actual reasoning underlying the model's decisions. We consider a setting in which an LLM provides both an answer and an explanation in response to a question. We identify two distinct dimensions of unfaithful explanations: incompleteness, meaning that the explanation omits factors that influence the answer, and unsoundness, meaning that the explanation cites factors that did not influence the model's answer. Existing approaches to improving LLM faithfulness include training-time methods, which require access to model weights and extensive computational resources, and test-time methods that largely focus on addressing unsoundness. We introduce a test-time approach that directly targets incompleteness. We remove from the input the concepts not credited in the model's explanation and re-query the model on the reduced input. This eliminates unmentioned influences while preserving the influence of mentioned concepts. Across two datasets, multiple model families, and two independent faithfulness metrics, our approach improves explanation faithfulness compared to both standard prompting and prompting to encourage faithfulness. Our method is model-agnostic and can be applied at inference time without modifying model parameters, providing a flexible mechanism for reducing hidden influences and improving the reliability and safety of LLM-assisted decision making.

Subjects:

Artificial Intelligence (cs.AI); Computation and Language (cs.CL)

Cite as: arXiv:2609.04343 [cs.AI]

(or arXiv:2609.04343v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2609.04343

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: S. Mazdak Abulnaga [view email] [v1] Thu, 3 Sep 2026 18:09:26 UTC (1,881 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled A Removal Based Approach to Improve LLM Faithfulness at Test-Time, by Qinglan Luo and S M A Nahian and John Guttag and S. Mazdak Abulnaga and Katie Matton

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.AI

new | recent | 2026-09

Change to browse by:

cs cs.CL

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • LLM explanations can be unfaithful in two ways: incompleteness and unsoundness
  • Proposed test-time method targets incompleteness by removing unmentioned concepts and re-querying
  • Approach improves faithfulness versus standard prompting and explicit faithfulness prompts
  • Model-agnostic and requires no parameter updates

Highlights and analysis are generated automatically and may contain errors. Check the original source.