0

Liangming Pan

Papers
19

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
Semantic Scholar
Attribution policy →
19papers

Authored papers

19

Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units

arXiv 2026

2026

Atomic Skills are the Prerequisite: When Reinforcement Learning Synthesizes Compositional Reasoning, and When It Only Amplifies

arXiv 2025

2026

InductionBench: LLMs Fail in the Simplest Complexity Class

arXiv 2025

2025

Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement

arXiv 2024

2024

Faithful Logical Reasoning via Symbolic Chain-of-Thought

arXiv 2024

2024

A Survey on Data Selection for Language Models

arXiv 2024

2024

SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation

arXiv 2024

2024

AntiLeak-Bench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge

arXiv 2024

2024

RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarios

arXiv 2024

2024

Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning

arXiv 2023

2023

A Survey on Detection of LLMs-Generated Content

arXiv 2023

2023

Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers

arXiv 2023

2023

INSTRUCTSCORE: Explainable Text Generation Evaluation with Finegrained Feedback

arXiv 2023

2023

Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies

arXiv 2023

2023

InfoCTM: A Mutual Information Maximization Perspective of Cross-Lingual Topic Modeling

arXiv 2023

2023

MAF: Multi-Aspect Feedback for Improving Reasoning in Large Language Models

arXiv 2023

2023

Knowledge of Knowledge: Exploring Known-Unknowns Uncertainty with Large Language Models

arXiv 2023

2023

Attacking Open-domain Question Answering by Injecting Misinformation

contraqa-question-answering-under

2021

KQA Pro: A Dataset with Explicit Compositional Programs for Complex Question Answering over Knowledge Base

ACL 2022 5

2020

Affiliations

No known affiliations.

Frequent co-authors

10

from 19 papers