paper-with-me

Papers

Enhancing Numerical Reasoning with the Guidance of Reliable Reasoning Processes

2024-02-16 · Dingzirui Wang, Longxu Dou, Xuanliang Zhang, Qingfu Zhu, Wanxiang Che

Numerical reasoning is an essential ability for NLP systems to handle numeric information. Recent research indicates that fine-tuning a small-scale model to learn generating reasoning processes alongside answers can significantly enhance performance. However, current methods have the limitation that most methods generate reasoning processes with large language models (LLMs), which are "unreliable" since such processes could contain information unrelated to the answer. To address this limitation, we introduce Enhancing NumeriCal reasOning with Reliable procEsses (Encore), which derives the reliable reasoning process by decomposing the answer formula, ensuring which fully supports the answer. Nevertheless, models could lack enough data to learn the reasoning process generation adequately, since our method generates only one single reasoning process for one formula. To overcome this difficulty, we present a series of pre-training tasks to help models learn the reasoning process generation with synthesized data. The experiments show that Encore yields improvement on all five experimental datasets with an average of 1.8%, proving the effectiveness of our method.

📄 PDF Abstract BibTeX arXiv:2402.10654

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Plan Then Action:High-Level Planning Guidance Reinforcement Learning for LLM Reasoning

2025-10-02 · Zhihao Dou, Qinjian Zhao, Zhongwei Wan, Dinggen Zhang 외 arxiv

Large language models (LLMs) demonstrate strong reasoning abilities via Chain-of-Thought (CoT), but their token-level generation encourages local decisions and lacks global planning, often leading to redundant or inaccur…

Reinforcement Learning

SRR-Judge: Step-Level Rating and Refinement for Enhancing Search-Integrated Reasoning in Search Agents

2026-02-08 · Chen Zhang, Kuicai Dong, Dexun Li, Wenjun Li 외 arxiv

Recent deep search agents built on large reasoning models (LRMs) excel at complex question answering by iteratively planning, acting, and gathering evidence, a capability known as search-integrated reasoning. However, ma…

Question Answering

Enhancing the Reasoning Capabilities of Small Language Models via Solution Guidance Fine-Tuning

2024-12-13 · Jing Bi, Yuting Wu, Weiwei Xing, Zhenjie Wei

Large language models (LLMs) have demonstrated remarkable performance across a wide range of tasks. Advances in prompt engineering and fine-tuning techniques have further enhanced their ability to address complex reasoni…

Prompt Engineering

Enhancing Mathematical Reasoning in Large Language Models with Self-Consistency-Based Hallucination Detection

2025-04-13 · MingShan Liu, Shi Bo, Jialing Fang

Large language models (LLMs) have demonstrated strong mathematical reasoning capabilities but remain susceptible to hallucinations producing plausible yet incorrect statements especially in theorem proving, symbolic mani…

Answer SelectionAutomated Theorem ProvingComputational EfficiencyHallucination+1

BankMathBench: A Benchmark for Numerical Reasoning in Banking Scenarios

2026-02-19 · Yunseung Lee, Subin Kim, Youngjun Kwak, Jaegul Choo arxiv

Large language models (LLMs)-based chatbots are increasingly being adopted in the financial domain, particularly in digital banking, to handle customer inquiries about products such as deposits, savings, and loans. Howev…