Scholar

Zhiqi Huang

Google Scholar ID: YsMU02UAAAAJ

Capital One

Information RetrievalNatural Language ProcessingMachine Learning

Citations & Impact

All-time

Citations

262

H-index

i10-index

Publications

Co-authors

list available

Contact

Publications

20 items

Browse publications on Google Scholar (top-right) ↗

Resume (English only)

Academic Achievements

Paper 'Distillation versus Contrastive Learning: How to Train Your Rerankers' accepted at IJCNLP-AACL 2025
Paper 'Confidence-Based Response Abstinence: Improving LLM Trustworthiness via Activation-Based Uncertainty Estimation' to be presented at the 2nd UncertaiNLP Workshop, EMNLP 2025
Paper 'Uncertainty as Feature Gaps: Epistemic Uncertainty Quantification of LLMs in Contextual Question Answering' accepted at the Reliable ML Workshop, NeurIPS 2025
Developed TruthTorchLM, a tool for uncertainty quantification in LLMs, to be presented at EMNLP 2025
Published survey 'A Survey of Model Architectures in Information Retrieval', addressing IR model evolution and challenges in the LLM era
Published 'Soft Prompt Decoding for Multilingual Dense Retrieval' at SIGIR 2023
Published 'Optimizing Large-Scale Context Retrieval for End-to-End ASR' at INTERSPEECH 2024
Published 'Language Concept Erasure for Language-invariant Dense Retrieval' at EMNLP 2024, introducing the LANCER framework to enhance language-agnostic dense retrieval

Co-authors

6 total