We stand with Ukraine

We stand with Ukraine

Hanqi Yan

Orcid: 0000-0001-5034-4520

According to our database¹, Hanqi Yan authored at least 35 papers between 2019 and 2026.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of four.

Timeline

Legend:

Book In proceedings Article PhD thesis Dataset Other

Links

On csauthors.net:

Bibliography

2026

GRADE: Probing Knowledge Gaps in LLMs through Gradient Subspace Dynamics.

[DOI]

,

,

,

,

CoRR, April, 2026

Stop the Flip-Flop: Context-Preserving Verification for Fast Revocable Diffusion Decoding.

[DOI]

,

,

,

,

,

,

Philip Alexander Teare

,

,

,

Amrutha Saseendran

,

CoRR, February, 2026

Context Compression via Explicit Information Transmission.

[DOI]

,

,

,

,

,

CoRR, February, 2026

Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation.

[DOI]

,

,

,

,

CoRR, February, 2026

Not All Code Is Equal: A Data-Centric Study of Code Complexity and LLM Reasoning.

[DOI]

,

,

,

,

,

Helen Yannakoudakis

,

CoRR, January, 2026

AutoMonitor-Bench: Evaluating the Reliability of LLM-Based Misbehavior Monitor.

[DOI]

,

,

,

,

,

CoRR, January, 2026

Beyond Perplexity: Let the Reader Select Retrieval Summaries via Spectrum Projection Score.

[DOI]

,

,

,

,

,

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025

When Thinking Backfires: Mechanistic Insights Into Reasoning-Induced Misalignment.

[DOI]

,

,

,

,

CoRR, September, 2025

Spectrum Projection Score: Aligning Retrieved Summaries with Reader Models in Retrieval-Augmented Generation.

[DOI]

,

,

,

,

,

CoRR, August, 2025

SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers.

[DOI]

,

,

,

,

CoRR, April, 2025

Beyond Prompting: An Efficient Embedding Framework for Open-Domain Question Answering.

[DOI]

,

,

,

,

,

CoRR, March, 2025

The Multi-Faceted Monosemanticity in Multimodal Representations.

[DOI]

,

,

,

,

,

CoRR, February, 2025

Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration.

[DOI]

,

,

,

,

,

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Constrain Alignment with Sparse Autoencoders.

[DOI]

,

,

,

,

,

,

,

,

,

,

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Position: LLMs Need a Bayesian Meta-Reasoning Framework for More Robust and Generalizable Reasoning.

[DOI]

,

,

,

,

Proceedings of the Forty-second International Conference on Machine Learning, 2025

GraphMind: Interactive Novelty Assessment System for Accelerating Scientific Discovery.

[DOI]

Italo Luis da Silva

,

,

,

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation.

[DOI]

,

,

,

,

,

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

Beyond Prompting: An Efficient Embedding Framework for Open-Domain Question Answering.

[DOI]

,

,

,

,

,

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

Drift: Enhancing LLM Faithfulness in Rationale Generation via Dual-Reward Probabilistic Inference.

[DOI]

,

,

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

2024

Explainable Recommender With Geometric Information Bottleneck.

[DOI]

,

,

,

,

IEEE Trans. Knowl. Data Eng., July, 2024

Direct Preference Optimization Using Sparse Feature-Level Constraints.

[DOI]

,

,

,

,

,

,

,

,

,

,

CoRR, 2024

The Mystery of In-Context Learning: A Comprehensive Survey on Interpretation and Analysis.

[DOI]

,

,

,

,

,

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

Encourage or Inhibit Monosemanticity? Revisit Monosemanticity from a Feature Decorrelation Perspective.

[DOI]

,

,

,

,

,

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

Weak Reward Model Transforms Generative Models into Robust Causal Event Extraction Systems.

[DOI]

Italo Luis da Silva

,

,

,

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

Mirror: Multiple-perspective Self-Reflection Method for Knowledge-rich Reasoning.

[DOI]

,

,

,

,

Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024

Addressing Order Sensitivity of In-Context Demonstration Examples in Causal Language Models.

[DOI]

,

,

,

Proceedings of the Findings of the Association for Computational Linguistics, 2024

2023

Tracking Brand-Associated Polarity-Bearing Topics in User Reviews.

[DOI]

,

,

,

Trans. Assoc. Comput. Linguistics, 2023

The Mystery and Fascination of LLMs: A Comprehensive Survey on the Interpretation and Analysis of Emergent Abilities.

[DOI]

,

,

,

,

,

CoRR, 2023

Counterfactual Generation with Identifiability Guarantees.

[DOI]

,

,

,

,

,

,

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Distinguishability Calibration to In-Context Learning.

[DOI]

,

,

,

,

,

Proceedings of the Findings of the Association for Computational Linguistics: EACL 2023, 2023

2022

Hierarchical Interpretation of Neural Text Classification.

[DOI]

,

,

Comput. Linguistics, 2022

Addressing token uniformity in transformers via singular value transformation.

[DOI]

,

,

,

Proceedings of the Uncertainty in Artificial Intelligence, 2022

2021

Position Bias Mitigation: A Knowledge-Aware Graph Model for Emotion Cause Extraction.

[DOI]

,

,

Gabriele Pergola

,

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 2021

2020

Reinforcement Learning based Recommendation with Graph Convolutional Q-network.

[DOI]

,

,

,

Proceedings of the 43rd International ACM SIGIR conference on research and development in Information Retrieval, 2020

2019

LexicalAT: Lexical-Based Adversarial Reinforcement Training for Robust Sentiment Classification.

[DOI]

,

,

,

,

,

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 2019

Loading...