paper-with-me

홈 › Papers

Generalizing Numerical Reasoning in Table Data through Operation Sketches and Self-Supervised Learning

2026-04-23 · Hanjun Cho, Gahyun Yoo, Hanseong Kim, Jay-Yoon Lee arxiv

Numerical reasoning over expert-domain tables often exhibits high in-domain accuracy but limited robustness to domain shift. Models trained with supervised fine-tuning (SFT) on specific datasets tend to rely on header-operation shortcuts rather than structural reasoning. We introduce TaNOS, a continual pre-training framework comprising three components: (i) header anonymization to reduce lexical memorization, (ii) operation sketches that provide minimal structural cues, and (iii) self-supervised pretraining that constructs correctness-guaranteed program-question pairs from given tables in a program-first manner. By decoupling domain semantics and numerical operation structure, TaNOS improves the transferability of numerical reasoning. Applied to an 8B instruction-tuned model, TaNOS achieves 80.13% execution accuracy on FinQA with only 10% train data, outperforming SFT baseline (73.97%) with full train data and proprietary models such as GPT-5, Gemini-2.5-Pro. Furthermore, in the domain-shift experiments, TaNOS displays nearly-negligible cross-domain gap (<2pp) when standard SFT shows over 10pp gap. These results suggest that structural guidance with operation sketches, header-agnostic representations, and correctness-guaranteed self-supervision can improve the robustness of numerical reasoning across diverse expert-domain tables.

📄 PDF Abstract BibTeX arXiv:2604.21495

Code (0)

등록된 구현이 없습니다.

Tasks

Self-Supervised Learning

Similar Papers 제목 키워드 기반

Structural Encoding and Pre-training Matter: Adapting BERT for Table-Based Fact Verification

2021-04-01 · EACL 2021 2 · Rui Dong, David Smith

Growing concern with online misinformation has encouraged NLP research on fact verification. Since writers often base their assertions on structured data, we focus here on verifying textual statements given evidence in t…

Fact VerificationGraph Neural NetworkLanguage ModelingLanguage Modelling+5

Enhancing Analogical Reasoning in the Abstraction and Reasoning Corpus via Model-Based RL

2024-08-27 · JIhwan Lee, Woochang Sim, Sejin Kim, Sundong Kim

This paper demonstrates that model-based reinforcement learning (model-based RL) is a suitable approach for the task of analogical reasoning. We hypothesize that model-based RL can solve analogical reasoning tasks more e…

ARCModel-based Reinforcement Learning

NEURAL EXECUTION ENGINES

2020-01-01 · ICLR 2020 1 · Yujun Yan, Kevin Swersky, Danai Koutra, Parthasarathy Ranganathan 외

Turing complete computation and reasoning are often regarded as necessary pre- cursors to general intelligence. There has been a significant body of work studying neural networks that mimic general computation, but these…

FORTAP: Using Formulas for Numerical-Reasoning-Aware Table Pretraining

2021-09-15 · ACL 2022 5 · Zhoujun Cheng, Haoyu Dong, Ran Jia, Pengfei Wu 외

Tables store rich numerical data, but numerical reasoning over tables is still a challenge. In this paper, we find that the spreadsheet formula, which performs calculations on numerical values in tables, is naturally a s…

Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization

2024-05-23 · Boshi Wang, Xiang Yue, Yu Su, Huan Sun

We study whether transformers can learn to implicitly reason over parametric knowledge, a skill that even the most capable language models struggle with. Focusing on two representative reasoning types, composition and co…