12 citations · 50 across the 28 of their papers we have counts for
28 papers
When Load-Balancing Goes Too Far: Expert Pruning in Over-Dispersed Mixture-of-Experts Models
Berkcan Kapusuzoglu, Connor Pryor, Sangwoo Cho +4
Expert pruning reduces the memory and serving cost of Mixture-of-Experts (MoE) models by removing low-importance experts identified by the router, assuming router probabilities pro…
AREAs-Lab: An Interactive Environment for AI-driven Requirement Elicitation for AI Systems
Pengshan Cai, Zihao Zhang, Ting Jin +8
Building effective AI systems increasingly depends on writing high-quality task requirements, yet users often struggle to articulate the constraints, preferences, and edge cases th…
StreamHear: Domain-Adapted Pseudo-Labeling for Semi-Supervised Streaming Speech Recognition
Zefang Liu, Chenyang Zhu, Sangwoo Cho +3
Streaming automatic speech recognition (ASR) underperforms on domain-shifted target audio, where labeled in-domain data is costly to prepare while unlabeled audio is abundant. We p…
Ask, Don't Judge: Binary Questions for Interpretable LLM Evaluation and Self-Improvement
Sangwoo Cho, Kushal Chawla, Pengshan Cai +4
Evaluating LLM outputs remains a major bottleneck in NLP: human evaluation is expensive and slow, lexical metrics correlate poorly with human judgments on open-ended generation, an…
SAFARI: Scaling Long Horizon Agentic Fault Attribution via Active Investigation
Chenyang Zhu, Jiayu Yao, Kushal Chawla +10
As autonomous agents tackle increasingly complex multi-step, multi-agent tasks, their execution trajectories have scaled beyond the constraints of even the largest context windows.…
RECAP: Regression Evaluation for Continual Adaptation of Prompts
Harsh Deshpande, Kushal Chawla, Sangwoo Cho +2
Production agentic systems routinely face evolving constraints and must comply from the very next interaction. Scenarios like a tool-call notification changing a compliance thresho…
DIAL-SUMMER: A Structured Evaluation Framework of Hierarchical Errors in Dialogue Summaries
Sahana Ramnath, Nima Chitsazan, Mingyang Zhou +8
Dialogues are a predominant mode of communication for humans, and it is immensely helpful to have automatically generated summaries of them (e.g., to revise key points discussed in…
Skills Regularized Task Decomposition for Multi-task Offline Reinforcement Learning
Minjong Yoo, Sangwoo Cho, Honguk Woo
Reinforcement learning (RL) with diverse offline datasets can have the advantage of leveraging the relation of multiple tasks and the common skills learned across those tasks, henc…
When Reasoning Meets Information Aggregation: A Case Study with Sports Narratives
Yebowen Hu, Kaiqiang Song, Sangwoo Cho +5
Reasoning is most powerful when an LLM accurately aggregates relevant information. We examine the critical role of information aggregation in reasoning by requiring the LLM to anal…
Polarity Calibration for Opinion Summarization
Yuanyuan Lei, Kaiqiang Song, Sangwoo Cho +3
Opinion summarization is automatically generating summaries from a variety of subjective information, such as product reviews or political opinions. The challenge of opinions summa…
Can Large Language Models do Analytical Reasoning?
Yebowen Hu, Kaiqiang Song, Sangwoo Cho +4
This paper explores the cutting-edge Large Language Model with analytical reasoning on sports. Our analytical reasoning embodies the tasks of letting large language models count ho…
SportsMetrics: Blending Text and Numerical Data to Understand Information Fusion in LLMs
Yebowen Hu, Kaiqiang Song, Sangwoo Cho +4
Large language models hold significant potential for integrating various data types, such as text documents and database records, for advanced analytics. However, blending text and…
SPECTRUM: Speaker-Enhanced Pre-Training for Long Dialogue Summarization
Sangwoo Cho, Kaiqiang Song, Chao Zhao +2
Multi-turn dialogues are characterized by their extended length and the presence of turn-taking conversations. Traditional language models often overlook the distinct features of t…
InFoBench: Evaluating Instruction Following Ability in Large Language Models
Yiwei Qin, Kaiqiang Song, Yebowen Hu +7
This paper introduces the Decomposed Requirements Following Ratio (DRFR), a new metric for evaluating Large Language Models' (LLMs) ability to follow instructions. Addressing a gap…
Zebra: Extending Context Window with Layerwise Grouped Local-Global Attention
Kaiqiang Song, Xiaoyang Wang, Sangwoo Cho +2
This paper introduces a novel approach to enhance the capabilities of Large Language Models (LLMs) in processing and understanding extensive text sequences, a critical aspect in ap…
MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning
Fuxiao Liu, Xiaoyang Wang, Wenlin Yao +5
With the rapid development of large language models (LLMs) and their integration into large multimodal models (LMMs), there has been impressive progress in zero-shot completion of…
Unsupervised Multi-document Summarization with Holistic Inference
Haopeng Zhang, Sangwoo Cho, Kaiqiang Song +4
Multi-document summarization aims to obtain core information from a collection of documents written on the same topic. This paper proposes a new holistic framework for unsupervised…
DecipherPref: Analyzing Influential Factors in Human Preference Judgments via GPT-4
Yebowen Hu, Kaiqiang Song, Sangwoo Cho +3
Human preference judgments are pivotal in guiding large language models (LLMs) to produce outputs that align with human values. Human evaluations are also used in summarization tas…
OASum: Large-Scale Open Domain Aspect-based Summarization
Xianjun Yang, Kaiqiang Song, Sangwoo Cho +4
Aspect or query-based summarization has recently caught more attention, as it can generate differentiated summaries based on users' interests. However, the current dataset for aspe…
Toward Unifying Text Segmentation and Long Document Summarization
Sangwoo Cho, Kaiqiang Song, Xiaoyang Wang +2
Text segmentation is important for signaling a document's structure. Without segmenting a long document into topically coherent sections, it is difficult for readers to comprehend…
Salience Allocation as Guidance for Abstractive Summarization
Fei Wang, Kaiqiang Song, Hongming Zhang +6
Abstractive summarization models typically learn to capture the salient information from scratch implicitly. Recent literature adds extractive summaries as guidance for abstractive…
StreamHover: Livestream Transcript Summarization and Annotation
Sangwoo Cho, Franck Dernoncourt, Tim Ganter +7
With the explosive growth of livestream broadcasting, there is an urgent need for new summarization technology that enables us to create a preview of streamed content and tap into…
Better Highlighting: Creating Sub-Sentence Summary Highlights
Sangwoo Cho, Kaiqiang Song, Chen Li +3
Amongst the best means to summarize is highlighting. In this paper, we aim to generate summary highlights to be overlaid on the original documents to make it easier for readers to…
Self-Attention Network for Skeleton-based Human Action Recognition
Sangwoo Cho, Muhammad Hasan Maqbool, Fei Liu +1
Skeleton-based action recognition has recently attracted a lot of attention. Researchers are coming up with new approaches for extracting spatio-temporal relations and making consi…