Hexiang Tan

5 papers · 2023–2026 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (18) 🐣 Hot Topic Early Bird ❓ The Questioner

Venues

ACL (2) EMNLP (2) NAACL (1)

Top co-authors

Fei Sun (5) Yuanzhuo Wang (4) Xueqi Cheng (3) Huawei Shen (3) Du Su (3) Wanli Yang (2) Qi Cao (2) Xin Chen (2) Jingang Wang (2) Cen Jianhe (1)

Research topics

Artificial Intelligence (4) Deep Learning (4) Core AI (4) Machine Learning (3) Natural Language Processing (3) Learning Types · Machine Learning (3) Applications (2) Generation (2) Models (2) Core Methods (1) Learning Types · Deep Learning (1) Optimization & Theory (1) Resources & Methods (1)

Keywords

large language model (3) retrieval-augmented generation (2) semantic parsing (1) passage retrieval (1) confidence calibration (1) error detection (1) retrieved context (1) perturbation robustness (1) expected calibration error (1) unsupervised calibration (1) syntax tree (1) context merging (1) information conflict (1) knowledge conflict (1) llm-generated text detection (1) text-to-sql generation (1) syntactic feature (1) sql query generation (1) syntax tree feature (1) self-consistent error (1)

Papers

BaseCal: Unsupervised Confidence Calibration via Base Model Signals ACL 2026 PRDetect: Perturbation-Robust LLM-generated Text Detection Based on Syntax Tree NAACL 2025 Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs EMNLP 2025 Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts? ACL 2024 ReFSQL: A Retrieval-Augmentation Framework for Text-to-SQL Generation EMNLP 2023