Papers by Pengtao Xie

16 papers
An End-to-End Contrastive Self-Supervised Learning Framework for Language Understanding (2022.tacl-1)

Copied to clipboard

Challenge: Existing approaches to learning data representations using contrastive learning perform data augmentation and contrastive training separately.
Approach: They propose a framework that performs data augmentation and contrastive learning end-to-end . they propose to combine data augmented with text encoders to optimize for contrastive training .
Outcome: Experiments on GLUE and Gururangan datasets show the proposed framework is effective in NLP.
Self-supervised Regularization for Text Classification (2021.tacl-1)

Copied to clipboard

Challenge: Text classification models are prone to overfitting when limited texts are available for training.
Approach: They propose a data-dependent regularization approach based on self-supervised learning . they define auxiliary tasks on input data without using human-provided labels .
Outcome: Experiments on 17 text classification datasets demonstrate the effectiveness of the proposed method.
AutoLoRA: Automatically Tuning Matrix Ranks in Low-Rank Adaptation Based on Meta Learning (2024.naacl-long)

Copied to clipboard

Challenge: Large-scale pretraining followed by task-specific finetuning has achieved great success in various NLP tasks.
Approach: They propose a meta learning based framework for automatically identifying the optimal rank of each LoRA layer.
Outcome: The proposed framework is based on a meta learning based framework that can identify the optimal rank of each LoRA layer.
A Neural Architecture for Automated ICD Coding (P18-1)

Copied to clipboard

Challenge: Medical coding is time-consuming, expensive, and error prone.
Approach: They propose to use diagnosis descriptions (DDs) of a patient as inputs to select the most relevant ICD codes.
Outcome: The proposed algorithms perform on a clinical dataset with 59K patient visits.
A Multi-Level Optimization Framework for End-to-End Text Augmentation (2022.tacl-1)

Copied to clipboard

Challenge: Existing methods for text augmentation perform data augmentation and downstream tasks separately.
Approach: They propose a framework to perform text augmentation and the downstream task end-to-end.
Outcome: The proposed framework performs text augmentation and the downstream task end-to-end on a text classification dataset.
Towards Visual Question Answering on Pathology Images (2021.acl-short)

Copied to clipboard

Challenge: Pathology imaging is used for identifying the causes and effects of diseases or injuries.
Approach: They propose a pathological visual question answering framework to analyze pathology images and answer medical questions related to these images.
Outcome: The proposed framework performs self-supervised pretraining and finetuning end-to-end to learn powerful visual and textual representations jointly and automatically identifies and excludes noisy self-controlled examples from pretraining.
Can Prompts Rewind Time for LLMs? Evaluating the Effectiveness of Prompted Knowledge Cutoffs (2025.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) are widely used for temporal prediction tasks . however, their reliance on pretraining data can lead to contamination concerns .
Approach: They investigate the capability of prompting to simulate an earlier knowledge cutoff in large language models.
Outcome: The proposed model fails to induce forgetting when the forgotten content is not directly asked but causally related to the query.
MedDialog: Large-scale Medical Dialogue Datasets (2020.emnlp-main)

Copied to clipboard

Challenge: telemedicine is a medical practice that provides patient care remotely using video conferencing tools.
Approach: They build large-scale medical dialogue datasets to facilitate research . they pretrain several models on the Chinese MedDialog dataset and compare their performance .
Outcome: The proposed datasets show that models trained on MedDialog can generate doctor-like medical dialogues.
Improving the Language Understanding Capabilities of Large Language Models Using Reinforcement Learning (2025.findings-emnlp)

Copied to clipboard

Challenge: Instruction-fine-tuned large language models (LLMs) under 14B parameters underperform on NLU tasks . we explore a framework to improve the NLU capabilities of LLMs .
Approach: They propose to use Proximal Policy Optimization to improve NLU capabilities . they frame NLU as a reinforcement learning environment and optimize for reward signals .
Outcome: The proposed framework outperforms supervised fine-tuning on GLUE and superGLUE tasks.
BioTool: A Comprehensive Tool-Calling Dataset for Enhancing Biomedical Capabilities of Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: despite the success of large language models, their performance in highly specialized domains remains unsatisfactory.
Approach: They propose a biomedical tool-calling dataset designed for fine-tuning LLMs . the dataset contains 34 frequently used tools from the NCBI, Ensembl, and UniProt databases .
Outcome: The proposed dataset outperforms commercial LLMs on biomedical domains.
On the Generation of Medical Dialogs for COVID-19 (2021.acl-short)

Copied to clipboard

Challenge: under the pandemic of COVID-19, people experiencing COVI D19-related symptoms have a pressing need to consult doctors.
Approach: They develop a medical dialog system that can provide COVID19-related consultations . they use two dialog datasets containing conversations between doctors and patients .
Outcome: The proposed system can provide COVID19-related consultations, but is too small compared with general-domain dialog datasets.
On the Automatic Generation of Medical Imaging Reports (P18-1)

Copied to clipboard

Challenge: a complete medical imaging report contains multiple heterogeneous forms of information, including findings and tags . abnormal regions in medical images are difficult to identify and the reports are typically long, containing multiple sentences.
Approach: They propose a multi-task learning framework which predicts tags and generates paragraphs for abnormal regions in medical images.
Outcome: The proposed framework can generate long paragraphs on two publicly available datasets.
Defense against Prompt Injection Attacks via Mixture of Encodings (2025.naacl-short)

Copied to clipboard

Challenge: Large Language Models (LLMs) have emerged as a dominant approach for a wide range of NLP tasks, but external content embeds malicious instructions that manipulate the LLM’s output.
Approach: They propose a mixture of encodings defense mechanism which utilizes multiple character encodes to degrade LLM performance on certain NLP tasks.
Outcome: The proposed method achieves one of the lowest attack success rates under prompt injection attacks while maintaining high performance across all NLP tasks.
Structured Self-Supervised Pretraining for Commonsense Knowledge Graph Completion (2021.tacl-1)

Copied to clipboard

Challenge: Existing approaches focus on generating concepts that have direct and obvious relationships with existing concepts and lack an ability to generate unobvious concepts.
Approach: They propose a general graph-to-paths pretraining framework that leverages high-order structures in CKGs to capture high-level relationships between concepts.
Outcome: The proposed framework can capture high-order relationships between concepts in four special cases: long path, path-to-path, router, and graph-node-path.
MetaWeighting: Learning to Weight Tasks in Multi-Task Learning (2022.findings-acl)

Copied to clipboard

Challenge: Existing task weighting methods assign weights only based on training losses, while ignoring the gap between the training loss and generalization loss.
Approach: They propose a task weighting algorithm which automatically weights the tasks via a learning-to-learn paradigm and a multi-task text classification paradigm.
Outcome: Extensive experiments show that the proposed method outperforms existing methods in multi-task text classification.
Generalizable and Stable Finetuning of Pretrained Language Models on Low-Resource Texts (2024.naacl-long)

Copied to clipboard

Challenge: Pretrained language models have advanced natural language processing tasks significantly, but finetuning them on low-resource datasets presents significant challenges such as instability and overfitting.
Approach: They propose a regularization method based on attention-guided weight mixup for finetuning PLMs on low-resource datasets.
Outcome: The proposed method improves generalization and combats overfitting on two splits of the training dataset.

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