13 citations · 37 across the 22 of their papers we have counts for
23 papers
SWE-MISBEHAVIOR: Benchmarking and Mitigating Boundary Violations in Software Coding Agents
Do Xuan Trong, Duc Anh Nguyen, Do Xuan Long +12
We present SWE-MISBEHAVIOR, the first taxonomy and evaluation framework for diagnosing boundary-violating misbehaviors in coding agents. It contains 7.4K human-in-the-loop synthesi…
Retrieved But Not Reliable: A Survey on Attacks, and Defenses in Retrieval-Augmented Generation
Minh Tran, Cuong Dang, Tuc Nguyen +10
Retrieval-Augmented Generation (RAG) enhances large language models by grounding outputs in external knowledge, improving factuality and reducing hallucinations. At the same time,…
ARD: Agentic Autoregressive Diffusion for Long Video Consistency
Do Xuan Long, Yale Song, Min-Yen Kan +2
Synthesizing consistent and coherent long video remains a fundamental challenge. Existing methods suffer from semantic drift and narrative collapse over long horizons. We present A…
Anthropogenic Regional Adaptation in Multimodal Vision-Language Model
Samuel Cahyawijaya, Peerat Limkonchotiwat, Tack Hwa Wong +45
While the field of vision-language (VL) has achieved remarkable success in integrating visual and textual information across multiple languages and domains, there is still no dedic…
VISTA: A Test-Time Self-Improving Video Generation Agent
Do Xuan Long, Xingchen Wan, Hootan Nakhost +3
Despite rapid advances in text-to-video synthesis, generated video quality remains critically dependent on precise user prompts. Existing test-time optimization methods, successful…
Contextual Representation Flow Across Depth in State-Space and Transformer Architectures
Nhat M. Hoang, Do Xuan Long, Cong-Duy Nguyen +3
State Space Models (SSMs) have emerged as efficient, linear-time alternatives to Transformer-Based Models (TBMs) for long-context processing. However, their different mechanisms ra…
What Makes a Good Natural Language Prompt?
Do Xuan Long, Duy Dinh, Ngoc-Hai Nguyen +4
As large language models (LLMs) have progressed towards more human-like and human--AI communications have become prevalent, prompting has emerged as a decisive component. However,…
Beyond In-Context Learning: Aligning Long-form Generation of Large Language Models via Task-Inherent Attribute Guidelines
Do Xuan Long, Duong Ngoc Yen, Do Xuan Trong +5
In-context learning (ICL) is an important yet not fully understood ability of pre-trained large language models (LLMs). It can greatly enhance task performance using a few examples…
A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems
Zixuan Ke, Fangkai Jiao, Yifei Ming +9
Reasoning is a fundamental cognitive process that enables logical inference, problem-solving, and decision-making. With the rapid advancement of large language models (LLMs), reaso…
Multi-expert Prompting Improves Reliability, Safety, and Usefulness of Large Language Models
Do Xuan Long, Duong Ngoc Yen, Anh Tuan Luu +3
We present Multi-expert Prompting, a novel enhancement of ExpertPrompting (Xu et al., 2023), designed to improve the large language model (LLM) generation. Specifically, it guides…
LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs
Do Xuan Long, Hai Nguyen Ngoc, Tiviatis Sim +5
We present the first systematic evaluation examining format bias in performance of large language models (LLMs). Our approach distinguishes between two categories of an evaluation…
ToXCL: A Unified Framework for Toxic Speech Detection and Explanation
Nhat M. Hoang, Xuan Long Do, Duc Anh Do +2
The proliferation of online toxic speech is a pertinent problem posing threats to demographic groups. While explicit toxic speech contains offensive lexical signals, implicit one c…
Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling
Yiran Zhao, Wenyue Zheng, Tianle Cai +4
Safety of Large Language Models (LLMs) has become a critical issue given their rapid progresses. Greedy Coordinate Gradient (GCG) is shown to be effective in constructing adversari…
Do LLMs Work on Charts? Designing Few-Shot Prompts for Chart Question Answering and Summarization
Xuan Long Do, Mohammad Hassanpour, Ahmed Masry +3
A number of tasks have been proposed recently to facilitate easy access to charts such as chart QA and summarization. The dominant paradigm to solve these tasks has been to fine-tu…
Prompt Optimization via Adversarial In-Context Learning
Xuan Long Do, Yiran Zhao, Hannah Brown +6
We propose a new method, Adversarial In-Context Learning (adv-ICL), to optimize prompt for in-context learning (ICL) by employing one LLM as a generator, another as a discriminator…
ChatGPT as a Math Questioner? Evaluating ChatGPT on Generating Pre-university Math Questions
Phuoc Pham Van Long, Duc Anh Vu, Nhat M. Hoang +2
Mathematical questioning is crucial for assessing students problem-solving skills. Since manually creating such questions requires substantial effort, automatic methods have been e…
Aligning Large Language Models with Human Opinions through Persona Selection and Value--Belief--Norm Reasoning
Do Xuan Long, Kenji Kawaguchi, Min-Yen Kan +1
Reasoning and predicting human opinions with large language models (LLMs) is essential yet challenging. Current methods employ role-playing with personae but face two major issues:…
Modeling What-to-ask and How-to-ask for Answer-unaware Conversational Question Generation
Xuan Long Do, Bowei Zou, Shafiq Joty +4
Conversational Question Generation (CQG) is a critical task for machines to assist humans in fulfilling their information needs through conversations. The task is generally cast in…
UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning
Ahmed Masry, Parsa Kavehzadeh, Xuan Long Do +2
Charts are very popular for analyzing data, visualizing key insights and answering complex reasoning questions about data. To facilitate chart-based data analysis using natural lan…
Retrieving Multimodal Information for Augmented Generation: A Survey
Ruochen Zhao, Hailin Chen, Weishi Wang +8
As Large Language Models (LLMs) become popular, there emerged an important trend of using multimodality to augment the LLMs' generation ability, which enables LLMs to better intera…
OpenCQA: Open-ended Question Answering with Charts
Shankar Kantharaj, Xuan Long Do, Rixie Tiffany Ko Leong +3
Charts are very popular to analyze data and convey important insights. People often analyze visualizations to answer open-ended questions that require explanatory answers. Answerin…
CoHS-CQG: Context and History Selection for Conversational Question Generation
Xuan Long Do, Bowei Zou, Liangming Pan +3
Conversational question generation (CQG) serves as a vital task for machines to assist humans, such as interactive reading comprehension, through conversations. Compared to traditi…
ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning
Ahmed Masry, Do Xuan Long, Jia Qing Tan +2
Charts are very popular for analyzing data. When exploring charts, people often ask a variety of complex reasoning questions that involve several logical and arithmetic operations.…