Papers by Hoifung Poon
Pareto Optimal Learning for Estimating Large Language Model Errors (2024.acl-long)
Copied to clipboard
| Challenge: | Existing approaches for improving the correctness of LLMs include prompt engineering, retrieval methods, and a generative model. |
| Approach: | They propose a method that generates a risk score to estimate the probability of error in an LLM by integrating multiple sources of information. |
| Outcome: | The proposed method is well correlated with the true LLM error rate, thus facilitating error correction. |
DocLens: Multi-aspect Fine-grained Medical Text Evaluation (2024.acl-long)
Copied to clipboard
Yiqing Xie, Sheng Zhang, Hao Cheng, Pengfei Liu, Zelalem Gero, Cliff Wong, Tristan Naumann, Hoifung Poon, Carolyn Rose
| Challenge: | Medical text generation systems are widely used to assist with administrative work and highlight salient information to support decision-making. |
| Approach: | They propose a set of metrics to evaluate completeness, conciseness, and attribution of medical text at a fine-grained level. |
| Outcome: | The proposed framework exhibits substantially higher agreement with medical experts than existing metrics. |
The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding (2020.acl-demos)
Copied to clipboard
Xiaodong Liu, Yu Wang, Jianshu Ji, Hao Cheng, Xueyun Zhu, Emmanuel Awa, Pengcheng He, Weizhu Chen, Hoifung Poon, Guihong Cao, Jianfeng Gao
| Challenge: | MT-DNN is an open-source natural language understanding toolkit . it allows researchers and developers to train customized deep learning models . |
| Approach: | They present MT-DNN, an open-source natural language understanding toolkit . it is designed to facilitate rapid customization for a broad spectrum of NLU tasks . MT supports multi-task knowledge distillation, which can substantially compress a deep neural model without significant performance drop. |
| Outcome: | The proposed model can significantly compress a large model without significant performance drop. |
From Introspection to Best Practices: Principled Analysis of Demonstrations in Multimodal In-Context Learning (2025.naacl-long)
Copied to clipboard
| Challenge: | Motivated by in-context learning capabilities of Large Language Models (LLMs), multimodal LLMs with additional visual modality are also exhibited with similar ICL abilities when multiple image-text pairs are provided as demonstrations. |
| Approach: | They conduct systematic and principled evaluation of multimodal ICL for models of different scales on a broad spectrum of new yet critical tasks. |
| Outcome: | The proposed model performance improves on a broad spectrum of new yet critical tasks. |
Deep Probabilistic Logic: A Unifying Framework for Indirect Supervision (D18-1)
Copied to clipboard
| Challenge: | Indirect supervision is a promising direction to address the annotation bottleneck . end-to-end modeling with probabilistic logic is often intractable due to inference and learning . |
| Approach: | They propose a framework for indirect supervision that integrates deep learning with deep learning by combining probabilistic logic with deep-learning. |
| Outcome: | Experiments on biomedical machine reading demonstrate the potential of this framework. |
MetaScale: Test-Time Scaling with Evolving Meta-Thoughts (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches impose fixed cognitive structures that enhance performance in specific tasks but lack adaptability across diverse scenarios. |
| Approach: | They propose a test-time scaling framework based on meta-thoughts to improve performance . meta-thinkts are adaptive thinking strategies tailored to a given task . |
| Outcome: | Experimental results show that MetaScale outperforms standard inference approaches . it can scale more effectively with increasing sampling budgets and produces more structured responses . |
Continual Contrastive Finetuning Improves Low-Resource Relation Extraction (2023.acl-long)
Copied to clipboard
| Challenge: | Relation extraction (RE) has been challenging in low-resource domains and with limited resources. |
| Approach: | They propose to pretrain and finetune the RE model using consistent objectives of contrastive learning. |
| Outcome: | The proposed method outperforms PLM-based RE classifier on two document-level RE datasets. |
Knowledge-Rich Self-Supervision for Biomedical Entity Linking (2022.findings-emnlp)
Copied to clipboard
Sheng Zhang, Hao Cheng, Shikhar Vashishth, Cliff Wong, Jinfeng Xiao, Xiaodong Liu, Tristan Naumann, Jianfeng Gao, Hoifung Poon
| Challenge: | Entity linking is challenging in high-value domains with myriad entities . standard classification approaches suffer from the annotation bottleneck . |
| Approach: | They propose a self-supervised approach to learn domain knowledge for biomedical entity linking . it generates self-reported mention examples on unlabeled text and trains contextual encoder . |
| Outcome: | The proposed method outperforms existing methods by 20 points in accuracy on biomedical datasets. |
mDPO: Conditional Preference Optimization for Multimodal Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have attempted to apply DPO to multimodal scenarios but have found it challenging to achieve consistent improvement. |
| Approach: | They propose a multimodal DPO objective that prevents the over-prioritization of language-only preferences by also optimizing image preference. |
| Outcome: | The proposed method significantly improves performance on two multimodal LLMs of different sizes and three widely used benchmarks. |
Document-Level N-ary Relation Extraction with Multiscale Representation Learning (N19-1)
Copied to clipboard
| Challenge: | Existing work on cross-sentence relation extraction is limited to three consecutive sentences, which severely limits recall. |
| Approach: | They propose a multiscale neural architecture for document-level n-ary relation extraction that combines representations learned over various text spans throughout the document and across the subrelation hierarchy. |
| Outcome: | The proposed system outperforms existing methods on biomedical machine reading. |
Exploring the Boundaries of GPT-4 in Radiology (2023.emnlp-main)
Copied to clipboard
Qianchu Liu, Stephanie Hyland, Shruthi Bannur, Kenza Bouzid, Daniel Castro, Maria Wetscherek, Robert Tinn, Harshita Sharma, Fernando Pérez-García, Anton Schwaighofer, Pranav Rajpurkar, Sameer Khanna, Hoifung Poon, Naoto Usuyama, Anja Thieme, Aditya Nori, Matthew Lungren, Ozan Oktay, Javier Alvarez-Valle
| Challenge: | Recent success of general-domain large language models has changed the natural language processing paradigm towards a unified foundation model across domains and applications. |
| Approach: | They evaluate the performance of GPT-4 on a variety of radiology tasks . they find it outperforms or matches current SOTA radiology models . |
| Outcome: | The proposed model outperforms or matches current SOTA radiology models on a range of tasks. |
Compositional Zero-Shot Domain Transfer with Text-to-Text Models (2023.tacl-1)
Copied to clipboard
Fangyu Liu, Qianchu Liu, Shruthi Bannur, Fernando Pérez-García, Naoto Usuyama, Sheng Zhang, Tristan Naumann, Aditya Nori, Hoifung Poon, Javier Alvarez-Valle, Ozan Oktay, Stephanie L. Hyland
| Challenge: | Existing approaches to zero-shot domain transfer are limited by domain gap and lack of in-domain labels. |
| Approach: | They propose a compositional transfer learning framework (DoT51) that learns domain knowledge and task knowledge in a multi-task manner without access to in-domain labels. |
| Outcome: | The proposed framework outperforms the current state-of-the-art in zero-shot domain transfer by over 7 absolute points in accuracy on RadNLI. |
Targeted Adversarial Training for Natural Language Understanding (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing adversarial training approaches focus on making adversarials less expensive or regularizing rather than replacing the standard training objective. |
| Approach: | They propose an algorithm to introspect current mistakes and prioritize adversarial training steps to where the model errs the most. |
| Outcome: | The proposed algorithm improves adversarial training for natural language understanding by introspecting mistakes and prioritizing training steps to where the model errs the most. |
Modular Self-Supervision for Document-Level Relation Extraction (2021.emnlp-main)
Copied to clipboard
| Challenge: | Prior work on information extraction tends to focus on binary relations within sentences . practical applications often require extracting complex relations across large text spans . |
| Approach: | They propose to decompose document-level relation extraction into relation detection and argument resolution, taking inspiration from Davidsonian semantics. |
| Outcome: | The proposed method outperforms state-of-the-art methods in biomedical machine reading for precision oncology by 20 absolute F1 points. |
Context-faithful Prompting for Large Language Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models encode parametric knowledge about world facts but overly rely on it can cause incorrect predictions in context-sensitive NLP tasks. |
| Approach: | They propose to use opinion-based prompts and counterfactual demonstrations to improve LLM faithfulness to contexts. |
| Outcome: | The proposed methods improve faithfulness to contexts using opinion-based prompts and counterfactual demonstrations. |