Pith. sign in

REVIEW 1 cited by

Confidence-Aware Sub-Structure Beam Search (CABS): Mitigating Hallucination in Structured Data Generation with Large Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.00069 v1 pith:CKNZM6ZV submitted 2024-05-30 cs.CL cs.LG

classification cs.CLcs.LG
keywords datagenerationconfidencestructuredcabslevelsub-structurebeam
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large Language Models (LLMs) have facilitated structured data generation, with applications in domains like tabular data, document databases, product catalogs, etc. However, concerns persist about generation veracity due to incorrect references or hallucinations, necessitating the incorporation of some form of model confidence for mitigation. Existing confidence estimation methods on LLM generations primarily focus on the confidence at the individual token level or the entire output sequence level, limiting their applicability to structured data generation, which consists of an intricate mix of both independent and correlated entries at the sub-structure level. In this paper, we first investigate confidence estimation methods for generated sub-structure-level data. We introduce the concept of Confidence Network that applies on the hidden state of the LLM transformer, as a more targeted estimate than the traditional token conditional probability. We further propose Confidence-Aware sub-structure Beam Search (CABS), a novel decoding method operating at the sub-structure level in structured data generation. CABS enhances the faithfulness of structured data generation by considering confidence scores from the Confidence Network for each sub-structure-level data and iteratively refining the prompts. Results show that CABS outperforms traditional token-level beam search for structured data generation by 16.7% Recall at 90% precision averagely on the problem of product attribute generation.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Reflection-Window Decoding: Text Generation with Selective Refinement

    cs.CL 2025-02 conditional novelty 6.0 of 10

    Selectively refining uncertain windows during decoding improves text quality over greedy and beam search, with a theory formalizing why greedy decoding can miss the joint-probability-optimal response.

Pith tools