Papers by Hoifung Poon

15 papers
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

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

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

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

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

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations