AI Paper Atlas

Research map / Large language models / Agents, code and math

ELASTIC: Numerical Reasoning with Adaptive Symbolic Compiler

Jiaxin Zhang, Yashar Moshfeghi

NeurIPS 2022 · Large language models › Agents, code and math · approach: LLM-guided program synthesis · 9 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Memory Register for previous sub-program results (ablation)ELASTIC (RoBERTa-large) · FinQAprogram accuracy: 64.78 -> 65.21Improved
add Memory Register (ablation)ELASTIC (RoBERTa-large) · MathQAprogram accuracy: 82.68 -> 83.00Improved
add Memory Register for long memory departing distance (M-MDD > 5) (ablation)ELASTIC · MathQAprogram accuracyImproved
separate operator and operand generation (ELASTIC vs FinQANet) with RoBERTa-largeELASTIC · FinQA testexecution accuracy: 65.05 -> 68.96Improved
separate operator and operand generation vs FinQANet with RoBERTa-largeELASTIC · MathQA testprogram accuracy: 79.20 -> 83.00Improved
use RoBERTa-large instead of RoBERTa-base encoder (ablation)ELASTIC · MathQA testprogram accuracy: 82.27 -> 83.00Improved
use ELASTIC rather than FinQANet on programs with 3 or more stepsELASTIC · FinQA >=3 stepsprogram accuracy: 31.10 vs 31.65 (original FinQANet), 23.80 (retrained)Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy