Papers by Ee-Peng Lim
Enconter: Entity Constrained Progressive Sequence Generation via Insertion-based Transformer (2021.eacl-main)
Copied to clipboard
| Challenge: | Autoregressive language models do not perform well under hard lexical constraints as they lack fine control of content generation process. |
| Approach: | They propose a new insertion transformer that considers hard lexical constraints and imposes rules over objects in the generated text. |
| Outcome: | The proposed model outperforms baseline models in several performance metrics rendering it more suitable in practical applications. |
Thoughts to Target: Enhance Planning for Target-driven Conversation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Empirical results demonstrate that our method significantly improves the planning ability of LLMs, especially in target-driven conversations. |
| Approach: | They propose a two-stage framework to improve the LLMs’ capability in planning conversations towards designated targets by distilling natural language plans from a target-driven conversation corpus and generating new plans with demonstration-guided in-context learning. |
| Outcome: | The proposed framework improves the ability of conversational models to plan towards designated targets and can be used to build extensive conversational AI. |
LLM4Vis: Explainable Visualization Recommendation using ChatGPT (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Existing methods to perform visualization recommendation require a large corpus of dataset-visualization pairs for training and lack natural explanations for their results. |
| Approach: | They propose a new method that uses a ChatGPT-based prompting approach to perform visualization recommendation and return human-like explanations using very few demonstration examples. |
| Outcome: | The proposed method outperforms or performs similarly to supervised learning models like Random Forest, Decision Tree, and MLP, in both few-shot and zero-shot settings. |
NOAHQA: Numerical Reasoning with Interpretable Graph Question Answering Dataset (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing question answering datasets lack numerical reasoning and reasoning processes . current research on numerical reasoning focuses on simple calculations . |
| Approach: | They propose a conversational and bilingual question answering dataset with numerical reasoning with compound mathematical expressions. |
| Outcome: | The proposed model achieves 55.5 exact match scores while human performance is 89.7. |
Consistent Client Simulation for Motivational Interviewing-based Counseling (2025.acl-long)
Copied to clipboard
Yizhe Yang, Palakorn Achananuparp, Heyan Huang, Jing Jiang, Nicholas Gabriel Lim, Cameron Tan Shi Ern, Phey Ling Kit, Jenny Giam Xiuhui, John Pinto, Ee-Peng Lim
| Challenge: | Existing approaches to simulate human clients in mental health counseling are limited and cost prohibitive. |
| Approach: | They propose a framework that supports consistent client simulation for mental health counseling by tracking the mental state of a simulated client, controlling its state transitions, and generating for each state behaviors consistent with the client’s motivation, beliefs, preferred plan to change, and and receptivity. |
| Outcome: | The proposed framework can simulate human clients for mental health counseling tasks and achieve higher consistency than previous methods. |
LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models (2023.emnlp-main)
Copied to clipboard
Zhiqiang Hu, Lei Wang, Yihuai Lan, Wanyu Xu, Ee-Peng Lim, Lidong Bing, Xing Xu, Soujanya Poria, Roy Lee
| Challenge: | Large language models (LLMs) have shown unprecedented performance across various tasks. |
| Approach: | They propose an easy-to-use framework that integrates adapters into LLMs . they evaluate adapters on 14 datasets from two different reasoning tasks . |
| Outcome: | The proposed framework can be used to fine-tune open-access language models with task-specific data and instruction data. |
MIThinker: A Plug-and-Play Policy-Optimized Thinker For Motivational Interviewing Counseling (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing reasoning large language models (LLMs) generate responses without explicitly aligning thoughts with counseling techniques, limiting their effectiveness. |
| Approach: | They propose a lightweight thinking model that generates therapeutic thoughts to guide MI counseling agents in strategy selection and response generation. |
| Outcome: | The proposed model achieves theory-of-mind assessment comparable to state-of the-art systems with an order of magnitude less computation. |
Speaker Verification in Agent-generated Conversations (2024.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models have increased the capabilities of conversational AI to solve challenging dialogue problems. |
| Approach: | They propose a task to verify whether two sets of utterances originate from the same speaker. |
| Outcome: | The proposed task aims to verify whether two sets of utterances originate from the same speaker. |
LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay (2024.emnlp-main)
Copied to clipboard
Yihuai Lan, Zhiqiang Hu, Lei Wang, Yang Wang, Deheng Ye, Peilin Zhao, Ee-Peng Lim, Hui Xiong, Hao Wang
| Challenge: | Existing studies on LLM agents' social behaviors are lacking . previous studies focused on positive social behaviors, leaving research on negative social behaviors relatively scarce. |
| Approach: | They propose a framework that features a multi-agent system facilitating efficient communication and interaction with LLM agents. |
| Outcome: | The proposed framework is based on Avalon and evaluates on game success and analyzes agents’ social behaviors. |
Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models (2023.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have recently been shown to deliver impressive performance in various NLP tasks. |
| Approach: | They propose a plan-and-solve (PS) prompting that includes a few manual steps to generate reasoning steps and improves the quality of generated reasoning steps. |
| Outcome: | The proposed strategy outperforms Zero-shot-CoT on ten reasoning problems and has comparable performance to 8-shot CoT prompting on the math reasoning problem. |
Graph-to-Tree Learning for Solving Math Word Problems (2020.acl-main)
Copied to clipboard
| Challenge: | Existing tree-based neural models do not capture the relationships and order information among the quantities well. |
| Approach: | They propose a novel deep learning architecture that combines the merits of the graph-based encoder and tree-based decoder to generate better solution expressions. |
| Outcome: | The proposed framework outperforms the state-of-the-art on two available datasets significantly. |
Seeing Culture: A Benchmark for Visual Reasoning and Grounding (2025.emnlp-main)
Copied to clipboard
Burak Satar, Zhixin Ma, Patrick Amadeus Irawan, Wilfried Ariel Mulyawan, Jing Jiang, Ee-Peng Lim, Chong-Wah Ngo
| Challenge: | Multimodal vision-language models (VLMs) have made significant progress in cultural understanding tasks . but these datasets often fall short of providing cultural reasoning while underrepresenting many cultures. |
| Approach: | They propose a Seeing Culture Benchmark that requires VLMs to reason on culturally rich images in two stages. |
| Outcome: | The proposed approach requires VLMs to reason on culturally rich images in two stages . the Seeing Culture Benchmark identifies cultural reasoning shortcomings in multimodal models . |
MHSafeEval: Role-Aware Interaction-Level Evaluation of Mental Health Safety in Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluation frameworks assess isolated responses using coarse-grained taxonomies or static datasets. |
| Approach: | They propose a role-aware mental health safety taxonomy that characterizes clinically significant harm in terms of interactional roles an AI counselor adopts. |
| Outcome: | The proposed framework significantly improves failure-mode coverage and diagnostic granularity. |
The Whole is Better than the Sum: Using Aggregated Demonstrations in In-Context Learning for Sequential Recommendation (2024.findings-naacl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have shown excellent performance on various NLP tasks. |
| Approach: | They propose a method that integrates multiple demonstration users into one aggregated demonstration to improve sequential recommendation. |
| Outcome: | The proposed method outperforms state-of-the-art LLM-based sequential recommendation methods on three recommendation datasets. |
CAMI: A Counselor Agent Supporting Motivational Interviewing through State Inference and Topic Exploration (2025.acl-long)
Copied to clipboard
Yizhe Yang, Palakorn Achananuparp, Heyan Huang, Jing Jiang, Phey Ling Kit, Nicholas Gabriel Lim, Cameron Tan Shi Ern, Ee-Peng Lim
| Challenge: | Motivational Interviewing (MI) is a client-centered counseling technique designed to address ambivalence and facilitate behavior change in clients. |
| Approach: | They propose to use a STAR framework to evoke change talk by using large language models to assess MI skill competency, client’s state inference accuracy, topic exploration proficiency, and overall counseling success. |
| Outcome: | The proposed agent outperforms several state-of-the-art methods and shows more realistic counselor-like behavior. |
Guided Attention Multimodal Multitask Financial Forecasting with Inter-Company Relationships and Global and Local News (2022.acl-long)
Copied to clipboard
| Challenge: | Stock returns in financial markets are influenced by textual information from diverse sources. |
| Approach: | They propose a model that captures both global and local multimodal information for investment and risk management-related forecasting tasks. |
| Outcome: | The proposed model outperforms state-of-the-art models in several forecasting tasks and important real-world applications. |