Peifeng Wang
Scholar

Peifeng Wang

Google Scholar ID: 3jfQnM4AAAAJ
Research Scientist, Meta GenAI
Natural Language Processing
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
1,118
 
H-index
13
 
i10-index
15
 
Publications
16
 
Co-authors
0
 
Contact
Emailpeifengw@usc.eduCVOpen ↗GitHubOpen ↗LinkedInOpen ↗
Publications
3 items
References Improve LLM Alignment in Non-Verifiable Domains
2026
Cited
0
Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluators
2025
Cited
0
A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems
2025
Cited
0
Resume (English only)
Academic Achievements
  • "Direct Judgement Preference Optimization", EMNLP 2025.
  • "Evaluating judges as evaluators: The benchmark of llm-judges as test-time scaling evaluators", ICML 2025.
  • "DOMINO: A Dual-System for Multi-step Visual Language Reasoning", preprint 2023.
  • "SCOTT: Self-Consistent Chain-of-Thought Distillation", ACL 2023, Outstanding Paper Award.
  • "PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales", ICLR 2023.
  • "Contextualized Scene Imagination for Generative Commonsense Reasoning", ICLR 2022.
  • "Do Language Models Perform Generalizable Commonsense Inference?", ACL Findings 2021.
  • "Learning to Deceive Knowledge Graph Augmented Models via Targeted Perturbation", ICLR 2021.
  • "Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering", EMNLP 2020.
  • "Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering", EMNLP Findings 2020.
Co-authors
0 total
Co-authors: 0 (list not available)