Mengnan Du

Venues

Frequent coauthors

Papers

1. AdaJudge: Adaptive Multi-Perspective Judging for Reward Modeling
   ACL 2026 ·

   Yongliang Miao

   DBLP profile ↗ORCID search ↗
2. AdaptiveK: Complexity-Driven Sparse Autoencoders for Interpretable Language Model Representations
   ACL 2026 ·

   Yifei Yao

   DBLP profile ↗ORCID search ↗
3. DeepSieve: Information Sieving via LLM-as-a-Knowledge-Router
   EACL 2026 ·

   Minghao Guo

   DBLP profile ↗ORCID search ↗
4. Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering
   EACL 2026 ·

   Haiyan Zhao

   DBLP profile ↗ORCID search ↗
5. FaithLM: Towards Faithful Explanations for Large Language Models
   EACL 2026 ·

   Yu-Neng Chuang

   DBLP profile ↗ORCID search ↗
6. FinCall-Surprise: A Large Scale Multi-modal Benchmark for Earning Surprise Prediction
   ACL 2026 ·

   Dong Shu

   DBLP profile ↗ORCID search ↗
7. FinChart-Bench: Benchmarking Financial Chart Comprehension in Vision-Language Models
   ACL 2026 ·

   Dong Shu

   DBLP profile ↗ORCID search ↗
8. Fine-Grained Interpretation of Political Opinions in Large Language Models
   AAAI 2026 ·

   Jingyu Hu

   DBLP profile ↗ORCID search ↗
9. KnowThyself: An Agentic Assistant for LLM Interpretability
   AAAI 2026 ·

   Suraj Prasai

   DBLP profile ↗ORCID search ↗
10. LLM Agents in Law: Taxonomy, Applications, and Challenges
    ACL 2026 ·

    Shuang Liu

    DBLP profile ↗ORCID search ↗
11. SAE-FiRE: Enhancing Earnings Surprise Predictions Through Sparse Autoencoder Feature Selection
    ACL 2026 ·

    Huopu Zhang

    DBLP profile ↗ORCID search ↗
12. SAGE: An Agentic Explainer Framework for Interpreting SAE Features in Language Models
    EACL 2026 ·

    Jiaojiao Han

    DBLP profile ↗ORCID search ↗
13. A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models
    EMNLP 2025 ·

    Dong Shu

    DBLP profile ↗ORCID search ↗
14. Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders
    EMNLP 2025 ·

    Dong Shu

    DBLP profile ↗ORCID search ↗
15. Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution
    ICLR 2025 ·

    Haiyan Zhao

    DBLP profile ↗ORCID search ↗
16. Comparative Analysis of Demonstration Selection Algorithms for In-Context Learning in Large Language Models (Student Abstract)
    AAAI 2025 ·

    Dong Shu

    DBLP profile ↗ORCID search ↗
17. Concept-Centric Token Interpretation for Vector-Quantized Generative Models
    ICML 2025 ·

    Tianze Yang

    DBLP profile ↗ORCID search ↗
18. Data-centric NLP Backdoor Defense from the Lens of Memorization
    NAACL 2025 ·

    Zhenting Wang

    DBLP profile ↗ORCID search ↗
19. Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models
    EMNLP 2025 ·

    Zihao Li

    DBLP profile ↗ORCID search ↗
20. From Commands to Prompts: LLM-based Semantic File System for AIOS
    ICLR 2025 ·

    Zeru Shi

    DBLP profile ↗ORCID search ↗
21. Improving LLM Reasoning through Interpretable Role-Playing Steering
    EMNLP 2025 ·

    Anyi Wang

    DBLP profile ↗ORCID search ↗
22. Invisible Backdoor Attack against Self-supervised Learning
    CVPR 2025 ·

    Hanrong Zhang

    DBLP profile ↗ORCID search ↗
23. Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages
    AAAI 2025 ·

    Zihao Li

    DBLP profile ↗ORCID search ↗
24. Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability
    EMNLP 2025 ·

    Dong Shu

    DBLP profile ↗ORCID search ↗
25. Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding
    ICML 2025 ·

    Mingyu Jin

    DBLP profile ↗ORCID search ↗
26. NPC-TAG: Node Prompts for Classification on Text Attributed Graphs with LLMs
    ICDM 2025 ·

    Uras Varolgunes

    DBLP profile ↗ORCID search ↗
27. Physics-Informed Attention-Enhanced Fourier Neural Operator for Solar Magnetic Field Extrapolations
    ICDM 2025 ·

    Jinghao Cao

    DBLP profile ↗ORCID search ↗
28. SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models
    EMNLP 2025 ·

    Zirui He

    DBLP profile ↗ORCID search ↗
29. AI Driven Online Advertising: Market Design, Generative AI, and Ethics
    WWW 2024 ·

    Fengxiang He

    DBLP profile ↗ORCID search ↗
30. Data-Centric Explainable Debiasing for Improving Fairness in Pre-trained Language Models
    ACL 2024 ·

    Yingji Li

    DBLP profile ↗ORCID search ↗
31. Enhancing Fairness in In-Context Learning: Prioritizing Minority Samples in Demonstrations
    ICLR 2024 ·

    Jingyu Hu

    DBLP profile ↗ORCID search ↗
32. Explaining Time Series via Contrastive and Locally Sparse Perturbations
    ICLR 2024 ·

    Zichuan Liu

    DBLP profile ↗ORCID search ↗
33. LawLLM: Law Large Language Model for the US Legal System
    CIKM 2024 ·

    Dong Shu

    DBLP profile ↗ORCID search ↗
34. Secure Your Model: An Effective Key Prompt Protection Mechanism for Large Language Models
    NAACL 2024 ·

    Ruixiang Tang

    DBLP profile ↗ORCID search ↗
35. Strategic Demonstration Selection for Improved Fairness in LLM In-Context Learning
    EMNLP 2024 ·

    Jingyu Hu

    DBLP profile ↗ORCID search ↗
36. TVE: Learning Meta-attribution for Transferable Vision Explainer
    ICML 2024 ·

    Guanchu Wang

    DBLP profile ↗ORCID search ↗
37. The Impact of Reasoning Step Length on Large Language Models
    ACL 2024 ·

    Mingyu Jin

    DBLP profile ↗ORCID search ↗