Papers by Su Lee
Task Arithmetic can Mitigate Synthetic-to-Real Gap in Automatic Speech Recognition (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for speech recognition suffer from the synthetic-to-real gap . existing methods suffer from this distributional shift due to acoustic mismatches . |
| Approach: | They propose to use task arithmetic to fine-tune an ASR model on synthetic data to mitigate the synthetic-to-real gap. |
| Outcome: | The proposed method shows an improvement of 10.03% over baselines on the SLURP dataset. |
Put Chatbot into Its Interlocutor’s Shoes: New Framework to Learn Chatbot Responding with Intention (2021.naacl-main)
Copied to clipboard
| Challenge: | Currently, most work on improving the fluency and coherence of chatbots is focused on making them more human-like. |
| Approach: | They propose a framework to train chatbots to possess human-like intentions by making them learn from interactive conversation. |
| Outcome: | The proposed framework includes a guiding chatbot and an interlocutor model that plays the role of humans. |
QueryForm: A Simple Zero-shot Form Entity Query Framework (2023.findings-acl)
Copied to clipboard
Zifeng Wang, Zizhao Zhang, Jacob Devlin, Chen-Yu Lee, Guolong Su, Hao Zhang, Jennifer Dy, Vincent Perot, Tomas Pfister
| Challenge: | Form-like document understanding is a key yet under-investigated problem . endlessly training specialized models on new document types is not scalable in many practical scenarios. |
| Approach: | They propose to use large-scale query-entity pairs generated from form-like webpages to pre-train QueryForm. |
| Outcome: | The proposed framework sets state-of-the-art average F1 score on XFUND and Payment benchmarks. |
Unlocking Parameter-Efficient Fine-Tuning for Low-Resource Language Translation (2024.findings-naacl)
Copied to clipboard
| Challenge: | Parameter-efficient fine-tuning (PEFT) methods are important in low-resource language (LRL) Neural Machine Translation (NMT) but their practical effectiveness varies significantly across different languages. |
| Approach: | They evaluated the performance of 8 parameters-efficient fine-tuning methods with 15 architectures using the SacreBLEU score. |
| Outcome: | The Houlsby+Inversion adapter outperforms the baseline architectures in both in-domain and out-domain tests and the Houlson+Inverter achieves the best performance overall. |
UniSumEval: Towards Unified, Fine-grained, Multi-dimensional Summarization Evaluation for LLMs (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing benchmarks for summarization quality evaluation lack diverse input scenarios, focus on narrowly defined dimensions, and struggle with subjective and coarse-grained annotation schemes. |
| Approach: | They propose to use AI to help human annotations and identifie potentially hallucinogenic input texts. |
| Outcome: | The proposed benchmarks improve on existing benchmarks in terms of input diversity, granularity of human annotations, and evaluation dimensions. |
FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction (2022.acl-long)
Copied to clipboard
Chen-Yu Lee, Chun-Liang Li, Timothy Dozat, Vincent Perot, Guolong Su, Nan Hua, Joshua Ainslie, Renshen Wang, Yasuhisa Fujii, Tomas Pfister
| Challenge: | Form-like document understanding is a surging research topic due to its practical applications . form documents have unique challenges stemming from their structural characteristics . |
| Approach: | They propose a structure-aware sequence model that leverages spatial relationships between tokens in a form for more precise attention score calculation. |
| Outcome: | The proposed model outperforms existing methods with a more compact model size and less pre-training data. |
Federated Learning for Semantic Parsing: Task Formulation, Evaluation Setup, New Algorithms (2023.acl-long)
Copied to clipboard
| Challenge: | Neural semantic parsers have achieved remarkable performance in recent years, but they are data-hungry and require annotators to have intimate knowledge of formal programs. |
| Approach: | They propose a task where multiple clients collaboratively train one global model without sharing their semantic parsing data. |
| Outcome: | The proposed model improves performance on three widely adopted FL algorithms (FedAvg, FedOPT and FedProx) and clients with smaller datasets enjoy faster performance. |
Pre-Trained Multilingual Sequence-to-Sequence Models: A Hope for Low-Resource Language Translation? (2022.findings-acl)
Copied to clipboard
En-Shiun Lee, Sarubi Thillainathan, Shravan Nayak, Surangika Ranathunga, David Adelani, Ruisi Su, Arya McCarthy
| Challenge: | Pre-trained multilingual sequence-to-sequence models like mBART and mT5 can be used to translate low-resource languages, but their practical application is unclear. |
| Approach: | They conduct an empirical experiment in 10 languages to determine what can pre-trained multilingual sequence-to-sequence models like mBART do to translate low-resource languages? |
| Outcome: | The proposed models are robust to domain differences, but translations for unseen and typologically distant languages remain below 3.0 BLEU. |
Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Fine-tuning large language models for downstream tasks often leads to catastrophic forgetting, notably degrading the safety of original alignments. |
| Approach: | They propose to merge the weights of pre- and post-fine-tuned models to improve safety while enhancing performance. |
| Outcome: | Experiments across different downstream tasks and models validate the method’s practicality and effectiveness. |
Unveiling Narrative Reasoning Limits of Large Language Models with Trope in Movie Synopses (2024.findings-emnlp)
Copied to clipboard
Hung-Ting Su, Ya-Ching Hsu, Xudong Lin, Xiang-Qian Shi, Yulei Niu, Han-Yuan Hsu, Hung-yi Lee, Winston Hsu
| Challenge: | Large language models (LLMs) equipped with chain-of-thoughts (CoT) prompting have shown significant multi-step reasoning capabilities in factual content like mathematics, commonsense, and logic. |
| Approach: | They introduce a trope-wise querying approach to assess the abstract reasoning abilities of large language models (LLMs) and uncover their low performance. |
| Outcome: | The proposed approach boosts the F1 score by 11.8 points and also reduces the performance of the large language models (LLMs) it also shows that it can cause hallucinations in narrative content, reducing the performance. |
Towards Fine-grained Audio Captioning with Multimodal Contextual Fusion (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for audio captioning lack fine-grained detail and contextual accuracy due to limited unimodal or superficial information. |
| Approach: | They propose a two-stage automated pipeline that uses pretrained models to extract contextual cues from video . a large language model synthesizes these inputs to generate detailed and context-aware captions . |
| Outcome: | The proposed method is scalable and generates detailed and context-aware captions on large-scale audio datasets. |
Pseudo2Real: Task Arithmetic for Pseudo-Label Correction in Automatic Speech Recognition (2026.findings-acl)
Copied to clipboard
| Challenge: | ASR models can be used to correct accent-specific errors without ground truth . pseudo-labels inherit the teacher model's systematic biases, authors say . |
| Approach: | They propose a parameter-space correction technique that captures pseudo-label biases . they propose achieving up to 35% relative WER reduction on a pseudo-labeled target model . |
| Outcome: | The proposed model achieves 35% relative WER reduction on ten African accents with the Whisper tiny model. |
Enhancing Low-resource Fine-grained Named Entity Recognition by Leveraging Coarse-grained Datasets (2023.emnlp-main)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) often suffers from insufficient labeled data when the number of annotations exceeds several tens of labels. |
| Approach: | They propose a model with a fine-to- coarse mapping matrix to leverage hierarchical structure explicitly. |
| Outcome: | The proposed model outperforms both K-shot learning and supervised learning methods when dealing with a small number of fine-grained annotations. |
FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction (2023.acl-long)
Copied to clipboard
Chen-Yu Lee, Chun-Liang Li, Hao Zhang, Timothy Dozat, Vincent Perot, Guolong Su, Xiang Zhang, Kihyuk Sohn, Nikolay Glushnev, Renshen Wang, Joshua Ainslie, Shangbang Long, Siyang Qin, Yasuhisa Fujii, Nan Hua, Tomas Pfister
| Challenge: | Existing approaches that extend the mask language modeling to other modalities require careful multi-task tuning, complex reconstruction target designs, or additional pre-training data. |
| Approach: | They propose a centralized multimodal graph contrastive learning strategy to unify self-supervised pre-training for all modalities in one loss. |
| Outcome: | The proposed model achieves state-of-the-art performance on FUNSD, CORD, SROIE and Payment benchmarks with a more compact model size. |
Towards Multi-dimensional Evaluation of LLM Summarization across Domains and Languages (2025.acl-long)
Copied to clipboard
Hyangsuk Min, Yuho Lee, Minjeong Ban, Jiaqi Deng, Nicole Hee-Yeon Kim, Taewon Yun, Hang Su, Jason Cai, Hwanjun Song
| Challenge: | Existing evaluation frameworks for text summarization lack domain-specific assessment criteria and are predominantly English-centric. |
| Approach: | They propose a multi-dimensional, multi-domain evaluation of summarization in English and Chinese that incorporates specialized assessment criteria for each domain and leverages a debate system to enhance annotation quality. |
| Outcome: | The proposed evaluation framework provides a multi-dimensional, multi-domain evaluation of summarization in English and Chinese. |
LMDX: Language Model-based Document Information Extraction and Localization (2024.findings-acl)
Copied to clipboard
Vincent Perot, Kai Kang, Florian Luisier, Guolong Su, Xiaoyu Sun, Ramya Sree Boppana, Zilong Wang, Zifeng Wang, Jiaqi Mu, Hao Zhang, Chen-Yu Lee, Nan Hua
| Challenge: | Large Language Models have revolutionized Natural Language Processing but their application in extracting information from visually rich documents has not been successful. |
| Approach: | They propose a language model-based document information extraction and localization methodology to reframe the document information extract task for a LLM. |
| Outcome: | The proposed method enables extraction of singular, repeated, and hierarchical entities with and without training data. |
Learning to Summarize from LLM-generated Feedback (2025.naacl-long)
Copied to clipboard
| Challenge: | Developing effective text summarizers remains a challenge due to issues like unfaithful statements, key information omissions, and verbosity. |
| Approach: | They propose a large-scale dataset containing multi-dimensional feedback on LLM-generated summaries of varying quality across diverse domains to align them with human preferences for faithfulness, completeness, and conciseness. |
| Outcome: | The proposed model outperforms the 10x larger Llama3-70b-instruct in generating human-preferred summaries. |