English
Related papers

Related papers: ReaComp: Compiling LLM Reasoning into Symbolic Sol…

200 papers

Recent LLMs like DeepSeek-R1 have demonstrated state-of-the-art performance by integrating deep thinking and complex reasoning during generation. However, the internal mechanisms behind these reasoning processes remain unexplored. We…

Computation and Language · Computer Science 2025-08-07 Andrey Galichin , Alexey Dontsov , Polina Druzhinina , Anton Razzhigaev , Oleg Y. Rogov , Elena Tutubalina , Ivan Oseledets

Large Language Models (LLMs) have demonstrated remarkable proficiency in generating code. However, the misuse of LLM-generated (synthetic) code has raised concerns in both educational and industrial contexts, underscoring the urgent need…

Software Engineering · Computer Science 2024-12-17 Tong Ye , Yangkai Du , Tengfei Ma , Lingfei Wu , Xuhong Zhang , Shouling Ji , Wenhai Wang

Statutory law retrieval is a typical problem in legal language processing, that has various practical applications in law engineering. Modern deep learning-based retrieval methods have achieved significant results for this problem. However,…

Computation and Language · Computer Science 2024-10-17 Hai-Long Nguyen , Tan-Minh Nguyen , Duc-Minh Nguyen , Thi-Hai-Yen Vuong , Ha-Thanh Nguyen , Xuan-Hieu Phan

Enhancing reasoning capabilities remains a central focus in the LLM reasearch community. A promising direction involves requiring models to simulate code execution step-by-step to derive outputs for given inputs. However, as code is often…

Computation and Language · Computer Science 2025-07-15 Keqin Bao , Nuo Chen , Xiaoyuan Li , Binyuan Hui , Bowen Yu , Fuli Feng , Xiangnan He , Dayiheng Liu

Contemporary progress in large language models (LLMs) has revealed notable inferential capacities via reinforcement learning (RL) employing verifiable reward, facilitating the development of O1 and R1-like reasoning models. Directly…

Machine Learning · Computer Science 2025-10-21 Zexu Sun , Yongcheng Zeng , Erxue Min , Heyang Gao , Bokai Ji , Xu Chen

In enterprise search, building high-quality datasets at scale remains a central challenge due to the difficulty of acquiring labeled data. To resolve this challenge, we propose an efficient approach to fine-tune small language models (SLMs)…

LLMs show strong performance in code generation, but their outputs lack correctness guarantees. Sample-based uncertainty estimators address this by generating multiple candidate programs and measuring their disagreement. However, existing…

Software Engineering · Computer Science 2026-05-12 Weilin He , Arindam Sharma , Cristina David

Large Language Models (LLMs) can aid synthesis planning in chemistry, but standard prompting methods often yield hallucinated or outdated suggestions. We study LLM interactions with a reaction knowledge graph by casting reaction path…

Artificial Intelligence · Computer Science 2026-01-23 Olga Bunkova , Lorenzo Di Fruscia , Sophia Rupprecht , Artur M. Schweidtmann , Marcel J. T. Reinders , Jana M. Weber

Building precise simulations of the real world and invoking numerical solvers to answer quantitative problems is an essential requirement in engineering and science. We present FEABench, a benchmark to evaluate the ability of large language…

Artificial Intelligence · Computer Science 2025-04-09 Nayantara Mudur , Hao Cui , Subhashini Venugopalan , Paul Raccuglia , Michael P. Brenner , Peter Norgaard

Understanding and reasoning about code semantics is essential for enhancing code LLMs' abilities to solve real-world software engineering (SE) tasks. Although several code reasoning benchmarks exist, most rely on synthetic datasets or…

Software Engineering · Computer Science 2026-02-05 Monoshi Kumar Roy , Simin Chen , Benjamin Steenhoek , Jinjun Peng , Gail Kaiser , Baishakhi Ray , Wei Le

How do LLMs compare with symbolic tools on program synthesis tasks? We investigate this question on several synthesis domains: LTL reactive synthesis, syntax-guided synthesis, distributed protocol synthesis, and recursive function…

Programming Languages · Computer Science 2026-03-24 Derek Egolf , Yuhao Zhou , Stavros Tripakis

Large Language Models (LLMs) show strong capabilities in code generation, motivating their use in automated quantum solver development. However, in quantum computing, successful execution of generated code is not sufficient: correctness…

Software Engineering · Computer Science 2026-05-12 Luciano Baresi , Domenico Bianculli , Maryse Ernzer , Livia Lestingi , Fabrizio Pastore , Seung Yeob Shin

We introduce a large language model (LLM) based approach to answer complex questions requiring multi-hop numerical reasoning over financial reports. While LLMs have exhibited remarkable performance on various natural language and reasoning…

Computation and Language · Computer Science 2023-11-28 Karmvir Singh Phogat , Chetan Harsha , Sridhar Dasaratha , Shashishekar Ramakrishna , Sai Akhil Puranam

This paper investigates the capabilities of large language models (LLMs) in formulating and solving decision-making problems using mathematical programming. We first conduct a systematic review and meta-analysis of recent literature to…

Artificial Intelligence · Computer Science 2025-08-26 Mohammad J. Abdel-Rahman , Yasmeen Alslman , Dania Refai , Amro Saleh , Malik A. Abu Loha , Mohammad Yahya Hamed

While reasoning models (e.g., DeepSeek R1) trained with reinforcement learning (RL), excel in textual reasoning, they struggle in scenarios requiring structured problem-solving, such as geometric reasoning, concise computation, or complex…

Computation and Language · Computer Science 2025-04-18 Jiazhan Feng , Shijue Huang , Xingwei Qu , Ge Zhang , Yujia Qin , Baoquan Zhong , Chengquan Jiang , Jinxin Chi , Wanjun Zhong

Many structured prediction and reasoning tasks can be framed as program synthesis problems, where the goal is to generate a program in a domain-specific language (DSL) that transforms input data into the desired output. Unfortunately,…

Programming Languages · Computer Science 2024-11-04 Shraddha Barke , Emmanuel Anaya Gonzalez , Saketh Ram Kasibatla , Taylor Berg-Kirkpatrick , Nadia Polikarpova

LLM-based formal proof assistants (e.g., in Lean) hold great promise for automating mathematical discovery. But beyond syntactic correctness, do these systems truly understand mathematical structure as humans do? We investigate this…

Artificial Intelligence · Computer Science 2025-10-21 Haoyu Zhao , Yihan Geng , Shange Tang , Yong Lin , Bohan Lyu , Hongzhou Lin , Chi Jin , Sanjeev Arora

Pre-trained large language models (LMs) struggle to perform logical reasoning reliably despite advances in scale and compositionality. In this work, we tackle this challenge through the lens of symbolic programming. We propose DSR-LM, a…

Artificial Intelligence · Computer Science 2023-05-09 Hanlin Zhang , Jiani Huang , Ziyang Li , Mayur Naik , Eric Xing

Recent research has highlighted that Large Language Models (LLMs), even when trained to generate extended long reasoning steps, still face significant challenges on hard reasoning problems. However, much of the existing literature relies on…

Artificial Intelligence · Computer Science 2025-05-29 Fanzeng Xia , Yidong Luo , Tinko Sebastian Bartels , Yaqi Xu , Tongxin Li

Large language models (LLMs) have demonstrated strong performance in a wide-range of language tasks without requiring task-specific fine-tuning. However, they remain prone to hallucinations and inconsistencies, and often struggle with…

Computation and Language · Computer Science 2026-03-27 Matt Pauk , Maria Leonor Pacheco