Structured prompts can steer LLMs to flag certain unsupported claims and ambiguous pronouns, but performance varies sharply by model, context, and the syntactic role of the target, and the single test case was also the development case.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AI-Facilitated Analysis of Abstracts and Conclusions: Flagging Unsubstantiated Claims and Ambiguous Pronouns
Structured prompts can steer LLMs to flag certain unsupported claims and ambiguous pronouns, but performance varies sharply by model, context, and the syntactic role of the target, and the single test case was also the development case.