Pith. sign in

REVIEW 1 cited by

Learning to Reduce: Towards Improving Performance of Large Language Models on 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 2407.02750 v1 pith:GE3EM4GJ submitted 2024-07-03 cs.CL

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

Large Language Models (LLMs) have been achieving competent performance on a wide range of downstream tasks, yet existing work shows that inference on structured data is challenging for LLMs. This is because LLMs need to either understand long structured data or select the most relevant evidence before inference, and both approaches are not trivial. This paper proposes a framework, Learning to Reduce, that fine-tunes a language model with On-Policy Learning to generate a reduced version of an input structured data. When compared to state-of-the-art LLMs like GPT-4, Learning to Reduce not only achieves outstanding performance in reducing the input, but shows generalizability on different datasets. We further show that the model fine-tuned with our framework helps LLMs better perform on table QA tasks especially when the context is longer.

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. Beyond Vision: How Large Language Models Interpret Facial Expressions from Valence-Arousal Values

    cs.CV 2025-02 conditional novelty 5.0 of 10

    LLMs given only valence and arousal values classify facial expressions poorly but can generate free-text emotion descriptions that align with human annotations under Word2Vec and BERT similarity, though not under a ge...

Pith tools