Profiles2020-2026
Wai Lam
The Chinese University of Hong Kong
49Papers
26Last author
69Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers49
- APEX-SQL: Talking to the data via Agentic Exploration for Text-to-SQLAuthor 5 of 5KDD 2026 · 7 citations
- HGMem: Hypergraph-based Working Memory to Improve Multi-step RAG for Long-Context Complex Relational ModelingAuthor 6 of 7ICML 2026 · 4 citations
- Unveiling the Entropy Dynamics of Chain-of-Thought ReasoningAuthor 6 of 7ICML 2026 · 2 citations
- Multi-LLM Collaborative Search for Complex Problem SolvingAuthor 3 of 4ACL Findings 2026 · 1 citation
- The Essence of Contextual Understanding in Theory of Mind: A Study on Question Answering with Story CharactersAuthor 10 of 10ACL 2025 · 9 citations
- InfiniteICL: Breaking the Limit of Context Window Size via Long Short-term Memory TransformationAuthor 3 of 3ACL Findings 2025 · 1 citation
- SeqPO-SiMT: Sequential Policy Optimization for Simultaneous Machine TranslationAuthor 5 of 7ACL Findings 2025 · 1 citation
- SLoW: Select Low-frequency Words! Automatic Dictionary Selection for Translation on Large Language ModelsAuthor 4 of 4EMNLP 2025
- Plug-and-Play Policy Planner for Large Language Model Powered Dialogue AgentsAuthor 3 of 5ICLR 2024 · 86 citations
- On the Worst Prompt Performance of Large Language ModelsAuthor 5 of 5NeurIPS 2024 · 65 citations
- A Thorough Examination of Decoding Methods in the Era of LLMsAuthor 7 of 7EMNLP 2024 · 26 citations
- Asking Multimodal Clarifying Questions in Mixed-Initiative Conversational SearchAuthor 4 of 5WWW 2024 · 17 citations
- Chain-of-Dictionary Prompting Elicits Translation in Large Language ModelsAuthor 5 of 6EMNLP 2024 · 9 citations
- Reasons to Reject? Aligning Language Models with JudgmentsAuthor 4 of 5ACL Findings 2024 · 4 citations
- Consecutive Batch Model Editing with HooK LayersAuthor 6 of 6EMNLP 2024
- Not All Preference Pairs Are Created Equal: A Recipe for Annotation-Efficient Iterative Preference LearningAuthor 6 of 6EMNLP Findings 2024
- On the Effectiveness of Parameter-Efficient Fine-TuningAuthor 4 of 6AAAI 2023 · 234 citations
- Knowledge-enhanced Mixed-initiative Dialogue System for Emotional Support ConversationsAuthor 4 of 4ACL 2023 · 31 citations
- Enhancing Grammatical Error Correction Systems with ExplanationsAuthor 4 of 6ACL 2023 · 13 citations
- Product Question Answering in E-Commerce: A SurveyAuthor 4 of 4ACL 2023 · 9 citations
- Easy-to-Hard Learning for Information ExtractionAuthor 3 of 4ACL Findings 2023 · 8 citations
- DepWiGNN: A Depth-wise Graph Neural Network for Multi-hop Spatial Reasoning in TextAuthor 3 of 3EMNLP Findings 2023 · 3 citations
- Once Upon a Time in Graph: Relative-Time Pretraining for Complex Temporal ReasoningAuthor 4 of 4EMNLP 2023 · 1 citation
- TRIP: Accelerating Document-level Multilingual Pre-training via Triangular Document-level Pre-training on Parallel Data TripletsAuthor 5 of 8EMNLP Findings 2023
- User Satisfaction Estimation with Sequential Dialogue Act Modeling in Goal-oriented Conversational SystemsAuthor 3 of 5WWW 2022 · 34 citations
- PACIFIC: Towards Proactive Conversational Question Answering over Tabular and Textual Data in FinanceAuthor 4 of 5EMNLP 2022 · 25 citations
- Towards Generalizable and Robust Text-to-SQL ParsingAuthor 4 of 8EMNLP Findings 2022 · 9 citations
- ConReader: Exploring Implicit Relations in Contracts for Contract Clause ExtractionAuthor 6 of 6EMNLP 2022 · 7 citations
- McQueen: a Benchmark for Multimodal Conversational Query RewriteAuthor 7 of 7EMNLP 2022 · 6 citations
- Retrofitting Multilingual Sentence Embeddings with Abstract Meaning RepresentationAuthor 5 of 5EMNLP 2022 · 4 citations
Showing the 30 most recent indexed papers.
