Pith. sign in

REVIEW 2 cited by

Struc-Bench: Are Large Language Models Really Good at Generating Complex Structured Data?

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 2309.08963 v3 pith:DZCL5Z2D submitted 2023-09-16 cs.CL

classification cs.CL
keywords datallmsmodelsperformancestruc-benchacrossbenchmarkcomplex
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Despite the remarkable capabilities of Large Language Models (LLMs) like GPT-4, producing complex, structured tabular data remains challenging. Our study assesses LLMs' proficiency in structuring tables and introduces a novel fine-tuning method, cognizant of data structures, to bolster their performance. We unveil Struc-Bench, a comprehensive benchmark featuring prominent LLMs (GPT-NeoX-20B, GPT-3.5, GPT-4, and Vicuna), which spans text tables, HTML, and LaTeX formats. Our proposed FormatCoT aids in crafting format-specific instructions from the intended outputs to populate this benchmark. Addressing the gap in task-centered evaluation, we propose two innovative metrics, P-Score (Prompting Score) and H-Score (Heuristical Score), to more accurately gauge LLM performance. Our experiments show that applying our structure-aware fine-tuning to LLaMA-7B leads to substantial performance gains, outshining its LLM counterparts across most measures. In-depth error analysis and creating an ability map across six dimensions -- coverage, formatting, reasoning, comprehension, pragmatics, and hallucination -- highlight areas for future enhancements and suggest forthcoming research trajectories. Our code and models can be found at https://github.com/gersteinlab/Struc-Bench.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Towards Efficient and Effective Alignment of Large Language Models

    cs.CL 2025-06 conditional novelty 7.0 of 10

    A thesis presenting Lion, WebR, LTE, BMC, and FollowBench, five empirical methods that together address LLM alignment data, training, and evaluation.

  2. Classroom Simulacra: Building Contextual Student Generative Agents in Online Education for Learning Behavioral Simulation

    cs.HC 2025-02 conditional novelty 6.0 of 10

    A new reflection-based AI method makes LLM-generated virtual students predict real students' future quiz performance better than deep learning knowledge-tracing baselines.

Pith tools