5 citations · 10 across the 14 of their papers we have counts for
15 papers
PlaylistEval: Can Video-Language Judges Be Trusted at Day Scale and Beyond?
Shayekh Bin Islam, Hwanjun Song
Video-language models are increasingly used as judges of video understanding, both for evaluating model outputs and for training reward models. Whether their judgments remain relia…
Rethinking RAG in Long Videos: What to Retrieve and How to Use It?
Yuho Lee, Jisu Shin, Nicole Hee-Yeon Kim +5
Retrieval-augmented generation is extending beyond text to long videos, where query-relevant chunks can be represented across multiple modalities and temporal granularities. Progre…
Reasoning over Video: Evaluating How MLLMs Extract, Integrate, and Reconstruct Spatiotemporal Evidence
Seunghwan Bang, Hwanjun Song
The growing interest in embodied agents increases the demand for spatiotemporal video understanding, yet existing benchmarks largely emphasize extractive reasoning, where answers c…
Towards Multi-dimensional Evaluation of LLM Summarization across Domains and Languages
Hyangsuk Min, Yuho Lee, Minjeong Ban +6
Evaluation frameworks for text summarization have evolved in terms of both domain coverage and metrics. However, existing benchmarks still lack domain-specific assessment criteria,…
Faithful, Unfaithful or Ambiguous? Multi-Agent Debate with Initial Stance for Summary Evaluation
Mahnaz Koupaee, Jake W. Vincent, Saab Mansour +9
Faithfulness evaluators based on large language models (LLMs) are often fooled by the fluency of the text and struggle with identifying errors in the summaries. We propose an appro…
Learning to Verify Summary Facts with Fine-Grained LLM Feedback
Jihwan Oh, Jeonghwan Choi, Nicole Hee-Yeon Kim +2
Training automatic summary fact verifiers often faces the challenge of a lack of human-labeled data. In this paper, we explore alternative way of leveraging Large Language Model (L…
Learning to Summarize from LLM-generated Feedback
Hwanjun Song, Taewon Yun, Yuho Lee +4
Developing effective text summarizers remains a challenge due to issues like hallucinations, key information omissions, and verbosity in LLM-generated summaries. This work explores…
UniSumEval: Towards Unified, Fine-Grained, Multi-Dimensional Summarization Evaluation for LLMs
Yuho Lee, Taewon Yun, Jason Cai +2
Existing benchmarks for summarization quality evaluation often lack diverse input scenarios, focus on narrowly defined dimensions (e.g., faithfulness), and struggle with subjective…
FineSurE: Fine-grained Summarization Evaluation using LLMs
Hwanjun Song, Hang Su, Igor Shalyminov +2
Automated evaluation is crucial for streamlining text summarization benchmarking and model development, given the costly and time-consuming nature of human evaluation. Traditional…
Controllable Contextualized Image Captioning: Directing the Visual Narrative through User-Defined Highlights
Shunqi Mao, Chaoyi Zhang, Hang Su +3
Contextualized Image Captioning (CIC) evolves traditional image captioning into a more complex domain, necessitating the ability for multimodal reasoning. It aims to generate image…
TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization
Liyan Tang, Igor Shalyminov, Amy Wing-mei Wong +11
Single document news summarization has seen substantial progress on faithfulness in recent years, driven by research on the evaluation of factual consistency, or hallucinations. We…
Can Your Model Tell a Negation from an Implicature? Unravelling Challenges With Intent Encoders
Yuwei Zhang, Siffi Singh, Sailik Sengupta +4
Conversational systems often rely on embedding models for intent classification and intent clustering tasks. The advent of Large Language Models (LLMs), which enable instructional…
Semi-Supervised Dialogue Abstractive Summarization via High-Quality Pseudolabel Selection
Jianfeng He, Hang Su, Jason Cai +3
Semi-supervised dialogue summarization (SSDS) leverages model-generated summaries to reduce reliance on human-labeled data and improve the performance of summarization models. Whil…
MAGID: An Automated Pipeline for Generating Synthetic Multi-modal Datasets
Hossein Aboutalebi, Hwanjun Song, Yusheng Xie +7
Development of multimodal interactive systems is hindered by the lack of rich, multimodal (text, images) conversational data, which is needed in large quantities for LLMs. Previous…
Enhancing Abstractiveness of Summarization Models through Calibrated Distillation
Hwanjun Song, Igor Shalyminov, Hang Su +3
Sequence-level knowledge distillation reduces the size of Seq2Seq models for more efficient abstractive summarization. However, it often leads to a loss of abstractiveness in summa…