823 citations · 2.4k across the 165 of their papers we have counts for
175 papers
Unpacking the Compute Efficiency of Strong-to-Weak OPD against GRPO
Zeyu Leo Liu, Yang Li, Bo Pang +7
On-policy distillation (OPD) trains a student on its own rollouts under a frozen teacher's per-token supervision. Does this dense signal reduce the training FLOPs needed to reach a…
Aligning Text, Code, and Vision: A Multi-Objective Reinforcement Learning Framework for Text-to-Visualization
Mizanur Rahman, Mohammed Saidul Islam, Md Tahmid Rahman Laskar +2
Text-to-Visualization (Text2Vis) systems translate natural language queries over tabular data into concise answers and executable visualizations. While closed-source LLMs generate…
Deploying Tiny LVLM Judges for Real-World Evaluation of Chart Models: Lessons Learned and Best Practices
Md Tahmid Rahman Laskar, Mohammed Saidul Islam, Ridwan Mahbub +7
Large Vision-Language Models (LVLMs) with only 7B parameters have shown promise as automated judges in chart comprehension tasks. However, tiny models (<=2B parameters) still perfo…
LLM-Based Data Science Agents: A Survey of Capabilities, Challenges, and Future Directions
Mizanur Rahman, Amran Bhuiyan, Mohammed Saidul Islam +5
Recent advances in large language models (LLMs) have enabled a new class of AI agents that automate multiple stages of the data science workflow by integrating planning, tool use,…
CEMTM: Contextual Embedding-based Multimodal Topic Modeling
Amirhossein Abaskohi, Raymond Li, Chuyuan Li +2
We introduce CEMTM, a context-enhanced multimodal topic model designed to infer coherent and interpretable topic structures from both short and long documents containing text and i…
DashboardQA: Benchmarking Multimodal Agents for Question Answering on Interactive Dashboards
Aaryaman Kartha, Ahmed Masry, Mohammed Saidul Islam +8
Dashboards are powerful visualization tools for data-driven decision-making, integrating multiple interactive views that allow users to explore, filter, and navigate data. Unlike s…
From Charts to Fair Narratives: Uncovering and Mitigating Geo-Economic Biases in Chart-to-Text
Ridwan Mahbub, Mohammed Saidul Islam, Mir Tafseer Nayeem +4
Charts are very common for exploring data and communicating insights, but extracting key takeaways from charts and articulating them in natural language can be challenging. The cha…
Text2Vis: A Challenging and Diverse Benchmark for Generating Multimodal Visualizations from Text
Mizanur Rahman, Md Tahmid Rahman Laskar, Shafiq Joty +1
Automated data visualization plays a crucial role in simplifying data interpretation, enhancing decision-making, and improving efficiency. While large language models (LLMs) have s…
Learning Auxiliary Tasks Improves Reference-Free Hallucination Detection in Open-Domain Long-Form Generation
Chengwei Qin, Wenxuan Zhou, Karthik Abinav Sankararaman +10
Hallucination, the generation of factually incorrect information, remains a significant challenge for large language models (LLMs), especially in open-domain long-form generation.…
ChartQAPro: A More Diverse and Challenging Benchmark for Chart Question Answering
Ahmed Masry, Mohammed Saidul Islam, Mahir Ahmed +11
Charts are ubiquitous, as people often use them to analyze data, answer questions, and discover critical insights. However, performing complex analytical tasks with charts requires…
Multi2: Multi-Agent Test-Time Scalable Framework for Multi-Document Processing
Juntai Cao, Xiang Zhang, Raymond Li +4
Recent advances in test-time scaling have shown promising results in improving Large Language Model (LLM) performance through strategic computation allocation during inference. Whi…
Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Models
Shayekh Bin Islam, Md Asib Rahman, K S M Tozammel Hossain +3
Retrieval-Augmented Generation (RAG) has been shown to enhance the factual accuracy of Large Language Models (LLMs), but existing methods often suffer from limited reasoning capabi…
Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging Tasks
Xingxuan Li, Weiwen Xu, Ruochen Zhao +3
State-of-the-art large language models (LLMs) exhibit impressive problem-solving capabilities but may struggle with complex reasoning and factual correctness. Existing methods harn…
On Positional Bias of Faithfulness for Long-form Summarization
David Wan, Jesse Vig, Mohit Bansal +1
Large Language Models (LLMs) often exhibit positional bias in long-context settings, under-attending to information in the middle of inputs. We investigate the presence of this bia…
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…
DataNarrative: Automated Data-Driven Storytelling with Visualizations and Texts
Mohammed Saidul Islam, Md Tahmid Rahman Laskar, Md Rizwan Parvez +2
Data-driven storytelling is a powerful method for conveying insights by combining narrative techniques with visualizations and text. These stories integrate visual aids, such as hi…
Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey
Atsuyuki Miyai, Jingkang Yang, Jingyang Zhang +10
Detecting out-of-distribution (OOD) samples is crucial for ensuring the safety of machine learning systems and has shaped the field of OOD detection. Meanwhile, several other probl…
ChartGemma: Visual Instruction-tuning for Chart Reasoning in the Wild
Ahmed Masry, Megh Thakkar, Aayush Bajaj +3
Given the ubiquity of charts as a data analysis, visualization, and decision-making tool across industries and sciences, there has been a growing interest in developing pre-trained…
A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations
Md Tahmid Rahman Laskar, Sawsan Alqahtani, M Saiful Bari +10
Large Language Models (LLMs) have recently gained significant attention due to their remarkable capabilities in performing diverse tasks across various domains. However, a thorough…
XL-HeadTags: Leveraging Multimodal Retrieval Augmentation for the Multilingual Generation of News Headlines and Tags
Faisal Tareque Shohan, Mir Tafseer Nayeem, Samsul Islam +2
Millions of news articles published online daily can overwhelm readers. Headlines and entity (topic) tags are essential for guiding readers to decide if the content is worth their…
DnA-Eval: Enhancing Large Language Model Evaluation through Decomposition and Aggregation
Minzhi Li, Zhengyuan Liu, Shumin Deng +3
The acceleration of Large Language Models (LLMs) research has opened up new possibilities for evaluating generated texts. They serve as scalable and economical evaluators, but the…
Lifelong Event Detection with Embedding Space Separation and Compaction
Chengwei Qin, Ruirui Chen, Ruochen Zhao +2
To mitigate forgetting, existing lifelong event detection methods typically maintain a memory module and replay the stored memory data during the learning of a new task. However, t…
Prompt Leakage effect and defense strategies for multi-turn LLM interactions
Divyansh Agarwal, Alexander R. Fabbri, Ben Risher +3
Prompt leakage poses a compelling security and privacy threat in LLM applications. Leakage of system prompts may compromise intellectual property, and act as adversarial reconnaiss…
Relevant or Random: Can LLMs Truly Perform Analogical Reasoning?
Chengwei Qin, Wenhan Xia, Tan Wang +5
Analogical reasoning is a unique ability of humans to address unfamiliar challenges by transferring strategies from relevant past experiences. One key finding in psychology is that…