30 citations · 176 across the 66 of their papers we have counts for
71 papers
Abstain-R1: Calibrated Abstention and Post-Refusal Clarification via Verifiable RL
Skylar Zhai, Jingcheng Liang, Dongyeop Kang
Reinforcement fine-tuning improves the reasoning ability of large language models, but it can also encourage them to answer unanswerable queries by guessing or hallucinating missin…
The Amazing Agent Race: Strong Tool Users, Weak Navigators
Zae Myung Kim, Dongseok Lee, Jaehyung Kim +2
Existing tool-use benchmarks for LLM agents are overwhelmingly linear: our analysis of six benchmarks shows 55 to 100% of instances are simple chains of 2 to 5 steps. We introduce…
Scaling Unverifiable Rewards: A Case Study on Visual Insights
Shuyu Gan, James Mooney, Pan Hao +4
Large Language Model (LLM) agents can increasingly automate complex reasoning through Test-Time Scaling (TTS), iterative refinement guided by reward signals. However, many real-wor…
A2P-Vis: an Analyzer-to-Presenter Agentic Pipeline for Visual Insights Generation and Reporting
Shuyu Gan, Renxiang Wang, James Mooney +1
Automating end-to-end data science pipeline with AI agents still stalls on two gaps: generating insightful, diverse visual evidence and assembling it into a coherent, professional…
Mary, the Cheeseburger-Eating Vegetarian: Do LLMs Recognize Incoherence in Narratives?
Karin de Langis, Püren Öncel, Ryan Peters +4
Leveraging a dataset of paired narratives, we investigate the extent to which large language models (LLMs) can reliably separate incoherent and coherent stories. A probing study fi…
Tracing How Annotators Think: Augmenting Preference Judgments with Reading Processes
Karin de Langis, William Walker, Khanh Chi Le +1
We propose an annotation approach that captures not only labels but also the reading process underlying annotators' decisions, e.g., what parts of the text they focus on, re-read o…
FlowForge: Guiding the Creation of Multi-agent Workflows with Design Space Visualization as a Thinking Scaffold
Pan Hao, Dongyeop Kang, Nicholas Hinds +1
Multi-agent workflows have become an effective strategy for tackling complicated tasks by decomposing them into multiple sub-tasks and assigning them to specialized agents. However…
How LLMs Comprehend Temporal Meaning in Narratives: A Case Study in Cognitive Evaluation of LLMs
Karin de Langis, Jong Inn Park, Andreas Schramm +5
Large language models (LLMs) exhibit increasingly sophisticated linguistic capabilities, yet the extent to which these behaviors reflect human-like cognition versus advanced patter…
Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models
Zae Myung Kim, Chanwoo Park, Vipul Raheja +2
Reward-based alignment methods for large language models (LLMs) face two key limitations: vulnerability to reward hacking, where models exploit flaws in the reward signal; and reli…
Stealing Creator's Workflow: A Creator-Inspired Agentic Framework with Iterative Feedback Loop for Improved Scientific Short-form Generation
Jong Inn Park, Maanas Taneja, Qianwen Wang +1
Generating engaging, accurate short-form videos from scientific papers is challenging due to content complexity and the gap between expert authors and readers. Existing end-to-end…
LawFlow: Collecting and Simulating Lawyers' Thought Processes on Business Formation Case Studies
Debarati Das, Khanh Chi Le, Ritik Sachin Parkar +8
Legal practitioners, particularly those early in their careers, face complex, high-stakes tasks that require adaptive, context-sensitive reasoning. While AI holds promise in suppor…
Align to Structure: Aligning Large Language Models with Structural Information
Zae Myung Kim, Anand Ramachandran, Farideh Tavazoee +3
Generating long, coherent text remains a challenge for large language models (LLMs), as they lack hierarchical planning and structured organization in discourse generation. We intr…
Strong Memory, Weak Control: An Empirical Study of Executive Functioning in LLMs
Karin de Langis, Jong Inn Park, Bin Hu +5
Working memory, or the ability to hold and manipulate information in the mind, is a critical component of human intelligence and executive functioning. It is correlated with perfor…
ScholaWrite: A Dataset of End-to-End Scholarly Writing Process
Khanh Chi Le, Linghe Wang, Minhwa Lee +3
Writing is a cognitively demanding activity that requires constant decision-making, heavy reliance on working memory, and frequent shifts between tasks of different goals. To build…
Anchors Aweigh! Sail for Optimal Unified Multi-Modal Representations
Minoh Jeong, Zae Myung Kim, Min Namgung +3
A unified representation space in multi-modal learning is essential for effectively integrating diverse data sources, such as text, images, and audio, to enhance efficiency and per…
Human-AI Collaborative Taxonomy Construction: A Case Study in Profession-Specific Writing Assistants
Minhwa Lee, Zae Myung Kim, Vivek Khetan +1
Large Language Models (LLMs) have assisted humans in several writing tasks, including text revision and story generation. However, their effectiveness in supporting domain-specific…
Confidence Calibration and Rationalization for LLMs via Multi-Agent Deliberation
Ruixin Yang, Dheeraj Rajagopal, Shirley Anugrah Hayati +2
Uncertainty estimation is a significant issue for current large language models (LLMs) that are generally poorly calibrated and over-confident, especially with reinforcement learni…
Dynamic Multi-Reward Weighting for Multi-Style Controllable Generation
Karin de Langis, Ryan Koo, Dongyeop Kang
Textual style expresses a diverse set of information, including interpersonal dynamics (e.g., formality) and the author's emotions or attitudes (e.g., disgust). An open question is…
Chain-of-Instructions: Compositional Instruction Tuning on Large Language Models
Shirley Anugrah Hayati, Taehee Jung, Tristan Bodding-Long +4
Fine-tuning large language models (LLMs) with a collection of large and diverse instructions has improved the model's generalization to different tasks, even for unseen tasks. Howe…
II-MMR: Identifying and Improving Multi-modal Multi-hop Reasoning in Visual Question Answering
Jihyung Kil, Farideh Tavazoee, Dongyeop Kang +1
Visual Question Answering (VQA) often involves diverse reasoning scenarios across Vision and Language (V&L). Most prior VQA studies, however, have merely focused on assessing the m…
Threads of Subtlety: Detecting Machine-Generated Texts Through Discourse Motifs
Zae Myung Kim, Kwang Hee Lee, Preston Zhu +2
With the advent of large language models (LLM), the line between human-crafted and machine-generated texts has become increasingly blurred. This paper delves into the inquiry of id…
Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback
Daechul Ahn, Yura Choi, Youngjae Yu +2
Recent advancements in large language models have influenced the development of video large multimodal models (VLMMs). The previous approaches for VLMMs involved Supervised Fine-Tu…
Under the Surface: Tracking the Artifactuality of LLM-Generated Data
Debarati Das, Karin De Langis, Anna Martin-Boyle +14
This work delves into the expanding role of large language models (LLMs) in generating artificial data. LLMs are increasingly employed to create a variety of outputs, including ann…
SelectLLM: Can LLMs Select Important Instructions to Annotate?
Ritik Sachin Parkar, Jaehyung Kim, Jong Inn Park +1
Instruction tuning benefits from large and diverse datasets; however, creating such datasets involves a high cost of human labeling. While synthetic datasets generated by large lan…