Detecting Contextual Hallucinations in Large Language Models with Frequency-Aware Attention
Published in ICML 2026, 2026
A frequency-aware view of attention dynamics for lightweight contextual hallucination detection.
Publications
You can also find my articles on my Google Scholar profile.
HiMe: Real-Time Self-Hosted Personal Agent Platform for Health Insights with Wearable Devices
Published in EMNLP 2026 (System Demonstrations), 2026
A privacy-preserving, locally deployable LLM agent platform for real-time health insights from wearables.
Position: Self-Play Only Evolves When Self-Synthetic Pipeline Ensures Learnable Information Gain
Published in ICML 2026 (Position Paper Track), 2026
A position paper on why self-evolving LLM systems plateau and how to sustain self-improvement.
When Thinking Backfires: Mechanistic Insights into Reasoning-Induced Misalignment
Published in ICLR 2026, 2025
Mechanistic analysis of how strengthening reasoning capabilities can induce misalignment in LLMs.
Beyond Perplexity: Let the Reader Select Retrieval Summaries via Spectrum Projection Score
Published in AAAI 2026, 2025
A label-free metric for aligning retrieved summaries with reader models in retrieval-augmented generation.
NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement Learning
Published in EMNLP 2025, 2025
Incentive training for language models using verifier-free reinforcement learning approach.
Evaluating LLMs' Assessment of Mixed-Context Hallucination Through the Lens of Summarization
Published in Findings of ACL 2025, 2025
Evaluation of LLMs assessment capabilities for mixed-context hallucination in summarization tasks.
EnigmaToM: Improve LLMs' Theory-of-Mind Reasoning Capabilities with Neural Knowledge Base of Entity States
Published in Findings of ACL 2025, 2025
Improving LLMs theory-of-mind reasoning capabilities using neural knowledge base of entity states.
Can LLMs Simulate L2-English Dialogue? An Information-Theoretic Analysis of L1-Dependent Biases
Published in ACL 2025, 2025
Information-theoretic analysis of L1-dependent biases in LLM simulation of L2-English dialogue.
A Survey of Automatic Hallucination Evaluation on Natural Language Generation
Published in arXiv preprint, 2024
Comprehensive survey of automatic hallucination evaluation methods in natural language generation.
SAPGraph: Structure-aware extractive summarization for scientific papers with heterogeneous graph
Published in AACL-IJCNLP 2022, 2022
Structure-aware extractive summarization for scientific papers using heterogeneous graph neural networks.
Subjective bias in abstractive summarization
Published in arXiv preprint, 2021
Investigating subjective bias in abstractive summarization and its impact on summary quality.
CIST@CL-SciSumm 2020, LongSumm 2020: Automatic scientific document summarization
Published in SDP Workshop @ EMNLP 2020, 2020
Automatic scientific document summarization for CL-SciSumm 2020 and LongSumm 2020 shared tasks.