2 citations · 5 across the 10 of their papers we have counts for
10 papers
Controllable Conversational Theme Detection Track at DSTC 12
Igor Shalyminov, Hang Su, Jake Vincent +5
Conversational analytics has been on the forefront of transformation driven by the advances in Speech and Natural Language Processing techniques. Rapid adoption of Large Language M…
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…
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…
CERET: Cost-Effective Extrinsic Refinement for Text Generation
Jason Cai, Hang Su, Monica Sunkara +2
Large Language Models (LLMs) are powerful models for generation tasks, but they may not generate good quality outputs in their first attempt. Apart from model fine-tuning, existing…
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…