Guoxin Chen
Guoxin Chen has 4 papers in our library, in 2024–2025, most of them on Reasoning; often with Chengxi Li, Kai Fan, Minpeng Liao.
OpenAlex · ORCID · Wikidata · h-index 36 · 164 works · 4,632 citations OpenAlex, 2026-10-14
📄 4 works in our library · 🔗 Cited 141 times in our library · ⭐ Paper Stars ranking: #5938
Affiliations
Fields, topics and concepts
📚 Shelves 10The field of science this work belongs to (OpenAlex fields).Computer Science · 4 worksArtificial Intelligence · 4 worksBusiness, Management and Accounting · 1 workArts and Humanities · 3 worksComputational Theory and Mathematics · 2 worksLanguage and Linguistics · 3 worksManagement Information Systems · 1 workComputer Vision and Pattern Recognition · 1 workHealth Informatics · 1 workMedicine · 1 work
🧭 Topics 1Research subjects and languages the work is about.Reasoning · 2 works
Works by year
2020s
Papers
- AlphaMath Almost Zero: Process Supervision without Process (2024 · 120 citations)
Most recent work that improves LLM math reasoning fine-tunes models on step-by-step solutions written by human experts or GPT-4, which is costly to produce. - Table-Critic: A Multi-Agent Framework for Collaborative Criticism and Refinement in Table Reasoning (2025 · 25 citations)
Large language models often fail at multi-step reasoning over tables. A wrong choice early in the chain, such as picking the wrong row or column, tends to carry through to the final answer. Earlier decomposition methods like Binder, Dater and Chain-of-Table have no reliable way to catch and fix these intermediate… - DiReCT: Diagnostic Reasoning for Clinical Notes via Large Language Models (2024 · 20 citations)
LLMs such as GPT-4 score well on medical exam questions, but those benchmarks use short inputs and say little about whether a model's diagnostic reasoning can be inspected. - ReForm: Reflective Autoformalization with Prospective Bounded Sequence Optimization (2025 · 8 citations)
Autoformalization turns natural-language math problems into Lean statements that a machine can check. Current LLMs usually produce code that compiles, but the statements often change the problem's meaning. The authors argue this happens because models translate in one shot and never review their own output. ReForm…
Co-authors here
- Chengxi Li ×2
- Kai Fan ×2
- Minpeng Liao ×2
- Bowen Wang
- Dayiheng Liu
- Hajime Nagahara
- Jiahao Zhang
- Junhao Chen
- Peiying Yu
- Ruihua Song
- Wayne Xin Zhao
- Yuta Nakashima
Venues
- Conference on Neural Information Processing Systems (NeurIPS) ×2: NeurIPS 2024 ×2
- Annual Meeting of the Association for Computational Linguistics (ACL): ACL 2025
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/guoxin-chen/