English
Related papers

Related papers: Synthesis by Design: Controlled Data Generation vi…

200 papers

Human cognition exhibits systematic compositionality, the algebraic ability to generate infinite novel combinations from finite learned components, which is the key to understanding and reasoning about complex logic. In this work, we…

Computation and Language · Computer Science 2024-10-11 Jun Zhao , Jingqi Tong , Yurong Mou , Ming Zhang , Qi Zhang , Xuanjing Huang

Mathematical reasoning remains a challenging area for large language models (LLMs), prompting the development of math-specific LLMs such as LLEMMA, DeepSeekMath, and Qwen2-Math, among others. These models typically follow a two-stage…

Computation and Language · Computer Science 2025-03-25 Zui Chen , Tianqiao Liu , Mi Tian , Qing Tong , Weiqi Luo , Zitao Liu

Utilizing large language models (LLMs) for data augmentation has yielded encouraging results in mathematical reasoning. However, these approaches face constraints in problem diversity, potentially restricting them to in-domain/distribution…

Machine Learning · Computer Science 2024-09-25 Nuo Chen , Ning Wu , Jianhui Chang , Jia Li

We present Team asdfo123's submission to the LLMSR@XLLM25 shared task, which evaluates large language models on producing fine-grained, controllable, and interpretable reasoning processes. Systems must extract all problem conditions,…

Computation and Language · Computer Science 2025-05-20 Xinye Li , Mingqi Wan , Dianbo Sui

Large language models (LLMs), both proprietary and open-source, have demonstrated remarkable capabilities across various natural language processing tasks. However, they face significant limitations in legal reasoning tasks. Proprietary…

Computation and Language · Computer Science 2025-02-14 Zhi Zhou , Kun-Yang Yu , Shi-Yu Tian , Xiao-Wen Yang , Jiang-Xin Shi , Pengxiao Song , Yi-Xuan Jin , Lan-Zhe Guo , Yu-Feng Li

Program synthesis is the generation of a program from a specification. Correct synthesis is difficult, and methods that provide formal guarantees suffer from scalability issues. On the other hand, neural networks are able to generate…

Logic in Computer Science · Computer Science 2020-01-28 Elizabeth Polgreen , Ralph Abboud , Daniel Kroening

Many reasoning, planning, and problem-solving tasks share an intrinsic algorithmic nature: correctly simulating each step is a sufficient condition to solve them correctly. We collect pairs of naturalistic and synthetic reasoning tasks to…

While large models pre-trained on high-quality data exhibit excellent performance on mathematical reasoning (e.g., GSM8k, MultiArith), it remains challenging to specialize smaller models for these tasks. Common approaches to address this…

Computation and Language · Computer Science 2026-03-19 Neeraj Gangwar , Suma P Bhat , Nickvash Kani

Automatic detection of depression is a rapidly growing field of research at the intersection of psychology and machine learning. However, with its exponential interest comes a growing concern for data privacy and scarcity due to the…

Machine Learning · Computer Science 2024-11-27 Andrea Kang , Jun Yu Chen , Zoe Lee-Youngzie , Shuhao Fu

Large Language Models (LLMs) have exhibited impressive generation capabilities, but they suffer from hallucinations when solely relying on their internal knowledge, especially when answering questions that require less commonly known…

Computation and Language · Computer Science 2023-11-01 Wenting Zhao , Ye Liu , Tong Niu , Yao Wan , Philip S. Yu , Shafiq Joty , Yingbo Zhou , Semih Yavuz

In the past few years, Large Language Models (LLMs) have exploded in usefulness and popularity for code generation tasks. However, LLMs still struggle with accuracy and are unsuitable for high-risk applications without additional oversight…

Software Engineering · Computer Science 2024-10-29 William Murphy , Nikolaus Holzer , Feitong Qiao , Leyi Cui , Raven Rothkopf , Nathan Koenig , Mark Santolucito

Structured, procedural reasoning is essential for Large Language Models (LLMs), especially in mathematics. While post-training methods have improved LLM performance, they still fall short in capturing deep procedural logic on complex tasks.…

Artificial Intelligence · Computer Science 2025-08-27 Zhichao Yang , Zhaoxin Fan , Gen Li , Yuanze Hu , Xinyu Wang , Ye Qiu , Xin Wang , Yifan Sun , Wenjun Wu

The IPARC Challenge, inspired by ARC, provides controlled program synthesis tasks over synthetic images to evaluate automatic program construction, focusing on sequence, selection, and iteration. This set of 600 tasks has resisted automated…

Software Engineering · Computer Science 2025-06-23 Shraddha Surana , Ashwin Srinivasan , Michael Bain

Rapid advances in the field of Large Language Models (LLMs) have made LLM-based code generation an important area for investigation. An LLM-based code generator takes a prompt as input and produces code that implements the requirements…

Software Engineering · Computer Science 2026-05-11 Laboni Sarker , Mara Downing , Achintya Desai , Tevfik Bultan

Pre-trained Large Language Models (LLMs) are beginning to dominate the discourse around automatic code generation with natural language specifications. In contrast, the best-performing synthesizers in the domain of formal synthesis with…

Artificial Intelligence · Computer Science 2024-05-28 Yixuan Li , Julian Parsert , Elizabeth Polgreen

Existing approaches typically rely on large-scale fine-tuning to adapt LLMs for information reranking tasks, which is computationally expensive. In this work, we demonstrate that modern LLMs can be effectively adapted using only minimal,…

Computation and Language · Computer Science 2025-10-28 Tingyu Song , Yilun Zhao , Siyue Zhang , Chen Zhao , Arman Cohan

LLMs have shown impressive success in program synthesis, discovering programs that surpass prior solutions. However, these approaches rely on simple numeric scores to signal program quality, such as the value of the solution or the number…

Artificial Intelligence · Computer Science 2026-05-19 André G. Pereira , Augusto B. Corrêa , Jendrik Seipp

Synthesizing high-quality mathematical reasoning data without human priors remains a significant challenge. Current approaches typically rely on seed data mutation or simple prompt engineering, often suffering from mode collapse and limited…

Computation and Language · Computer Science 2026-04-14 Zixiong Yu , Jun Rao , Guhan Chen , Songtao Tian , Bohan Li , Jiansheng Wei , Min Zhang , Xiaojun Meng

Large Language Models (LLMs) have achieved remarkable success in tasks requiring complex reasoning, such as code generation, mathematical problem solving, and algorithmic synthesis -- especially when aided by reasoning tokens and…

Computation and Language · Computer Science 2025-06-13 Jaechul Roh , Varun Gandhi , Shivani Anilkumar , Arin Garg

Large Language Models (LLMs) have achieved significant advancements, but the increasing complexity of tasks and higher performance demands highlight the need for continuous improvement. Some approaches utilize synthetic data generated by…

Artificial Intelligence · Computer Science 2025-06-23 Haokun Zhao , Jinyi Han , Jiaqing Liang , Yanghua Xiao , Xiaojun Meng , Jiansheng Wei