Liangming Pan
- Papers
- 19
Cite
Notes
Only stored in your browser.
Authored papers
19Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units
arXiv 2026
Atomic Skills are the Prerequisite: When Reinforcement Learning Synthesizes Compositional Reasoning, and When It Only Amplifies
arXiv 2025
InductionBench: LLMs Fail in the Simplest Complexity Class
arXiv 2025
Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement
arXiv 2024
Faithful Logical Reasoning via Symbolic Chain-of-Thought
arXiv 2024
A Survey on Data Selection for Language Models
arXiv 2024
SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation
arXiv 2024
AntiLeak-Bench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge
arXiv 2024
RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarios
arXiv 2024
Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning
arXiv 2023
A Survey on Detection of LLMs-Generated Content
arXiv 2023
Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers
arXiv 2023
INSTRUCTSCORE: Explainable Text Generation Evaluation with Finegrained Feedback
arXiv 2023
Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies
arXiv 2023
InfoCTM: A Mutual Information Maximization Perspective of Cross-Lingual Topic Modeling
arXiv 2023
MAF: Multi-Aspect Feedback for Improving Reasoning in Large Language Models
arXiv 2023
Knowledge of Knowledge: Exploring Known-Unknowns Uncertainty with Large Language Models
arXiv 2023
Attacking Open-domain Question Answering by Injecting Misinformation
contraqa-question-answering-under
KQA Pro: A Dataset with Explicit Compositional Programs for Complex Question Answering over Knowledge Base
ACL 2022 5
Affiliations
Frequent co-authors
10from 19 papers