Pith. sign in

REVIEW 1 cited by

Injecting Numerical Reasoning Skills into 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 2004.04487 v1 pith:TYMWKV4Z submitted 2020-04-09 cs.CL

classification cs.CL
keywords reasoningdatamodelsnumericallargeperformancepre-trainedskills
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Large pre-trained language models (LMs) are known to encode substantial amounts of linguistic information. However, high-level reasoning skills, such as numerical reasoning, are difficult to learn from a language-modeling objective only. Consequently, existing models for numerical reasoning have used specialized architectures with limited flexibility. In this work, we show that numerical reasoning is amenable to automatic data generation, and thus one can inject this skill into pre-trained LMs, by generating large amounts of data, and training in a multi-task setup. We show that pre-training our model, GenBERT, on this data, dramatically improves performance on DROP (49.3 $\rightarrow$ 72.3 F1), reaching performance that matches state-of-the-art models of comparable size, while using a simple and general-purpose encoder-decoder architecture. Moreover, GenBERT generalizes well to math word problem datasets, while maintaining high performance on standard RC tasks. Our approach provides a general recipe for injecting skills into large pre-trained LMs, whenever the skill is amenable to automatic data augmentation.

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. E-Gen: Leveraging E-Graphs to Improve Continuous Representations of Symbolic Expressions

    cs.LG 2025-01 conditional novelty 6.0 of 10

    An e-graph-based data generator produces 55 million equivalent-expression training pairs, and embeddings trained on them beat prior math-embedding models and GPT-4o on several symbolic math tasks.

Pith tools