PaperTrail: A Claim-Evidence Interface for Grounding Provenance in LLM-based Scholarly Q&A

TL;DR

PaperTrail is an interface that enhances scholarly QA by decomposing LLM answers and sources into claims and evidence, improving provenance transparency and aiding verification, though it affects user trust and reliance.

Contribution

Introduces PaperTrail, a claim-evidence interface that maps LLM outputs and sources to improve provenance transparency in scholarly QA systems.

Findings

PaperTrail significantly reduced user trust compared to baseline.

Users continued relying on LLM outputs despite increased caution.

Claim-evidence matching aids understanding of LLM trustworthiness.

Abstract

Large language models (LLMs) are increasingly used in scholarly question-answering (QA) systems to help researchers synthesize vast amounts of literature. However, these systems often produce subtle errors (e.g., unsupported claims, errors of omission), and current provenance mechanisms like source citations are not granular enough for the rigorous verification that scholarly domain requires. To address this, we introduce PaperTrail, a novel interface that decomposes both LLM answers and source documents into discrete claims and evidence, mapping them to reveal supported assertions, unsupported claims, and information omitted from the source texts. We evaluated PaperTrail in a within-subjects study with 26 researchers who performed two scholarly editing tasks using PaperTrail and a baseline interface. Our results show that PaperTrail significantly lowered participants' trust compared to the baseline. However, this increased caution did not translate to behavioral changes, as people continued to rely on LLM-generated scholarly edits to avoid a cognitively burdensome task. We discuss the value of claim-evidence matching for understanding LLM trustworthiness in scholarly settings, and present design implications for cognition-friendly communication of provenance information.