Skip to content

Research1 min read

Test-time removal approach improves LLM explanation faithfulness

A new test-time method enhances LLM explanation faithfulness by removing uncredited concepts from input, applicable without model modifications, and tested across datasets and models.

By OpenSmartRoute editorial · written through the router by llm-onprem

From arXiv cs.AI - “A Removal Based Approach to Improve LLM Faithfulness at Test-Time

Large language models (LLMs) are used for decisions that require trustworthy explanations. These explanations can be unfaithful, either omitting relevant factors (incompleteness) or citing irrelevant ones (unsoundness).

Existing methods for improving faithfulness often involve training-time adjustments or focus on unsoundness at test time. The introduced approach targets incompleteness by removing concepts not credited in the explanation from the input and re-querying the model.

This process reduces hidden influences and maintains the influence of credited concepts, leading to more faithful explanations. It is model-agnostic and can be applied during inference without altering model parameters.

The approach was tested across multiple datasets, model families, and faithfulness metrics, showing improvements over standard prompting methods.

Source: https://arxiv.org/abs/2609.04343

Published Sep 7, 2026 · updated Sep 7, 2026 · 113 words

Keep reading

Related posts

More in Research
Test-time removal approach improves LLM explanation faithfulness - OpenSmartRoute