Papers
arxiv:2412.13175

DnDScore: Decontextualization and Decomposition for Factuality Verification in Long-Form Text Generation

Published on Dec 17, 2024
Authors:
,
,

Abstract

The study evaluates how decomposition and decontextualization interact in LLM verification pipelines and proposes DnDScore to handle augmented subclaims.

The decompose-then-verify strategy for verification of Large Language Model (LLM) generations decomposes claims that are then independently verified. Decontextualization augments text (claims) to ensure it can be verified outside of the original context, enabling reliable verification. While decomposition and decontextualization have been explored independently, their interactions in a complete system have not been investigated. Their conflicting purposes can create tensions: decomposition isolates atomic facts while decontextualization inserts relevant information. Furthermore, a decontextualized subclaim presents a challenge to the verification step: what part of the augmented text should be verified as it now contains multiple atomic facts? We conduct an evaluation of different decomposition, decontextualization, and verification strategies and find that the choice of strategy matters in the resulting factuality scores. Additionally, we introduce DnDScore, a decontextualization aware verification method which validates subclaims in the context of contextual information.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2412.13175
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2412.13175 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2412.13175 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2412.13175 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.