Papers by Jie Shao

19 papers
Are Large Pre-Trained Language Models Leaking Your Personal Information? (2022.findings-emnlp)

Copied to clipboard

Challenge: Pre-trained language models (PLMs) are prone to leaking personal information due to memorization, but the risk of specific personal information being extracted by attackers is low.
Approach: They analyze whether large pre-trained language models are prone to leaking personal information due to memorization.
Outcome: The proposed model is weak at association, so the risk of specific personal information being extracted by attackers is low.
The Tug of War Within: Mitigating the Fairness-Privacy Conflicts in Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Existing methods to enhance an LLM's privacy awareness with thousands of samples decrease its fairness awareness.
Approach: They propose a training-free method to Suppress the Privacy and faIrness coupled Neurons (SPIN) which theoretically and empirically decreases the mutual information between fairness and privacy awareness.
Outcome: The proposed method reduces the mutual information between fairness and privacy awareness without compromising general capabilities.
Retrieving Sequential Information for Non-Autoregressive Neural Machine Translation (P19-1)

Copied to clipboard

Challenge: Experimental results show that the Reinforce-NAT system surpasses the baseline NAT system by a significant margin on BLEU without decelerating the decoding speed.
Approach: They propose a sequence-level training method and a Transformer decoder to fuse the target sequential information into the top layer of the decoded Transformer.
Outcome: The proposed model surpasses the baseline NAT system on BLEU without decelerating the decoding speed and achieves comparable translation performance to the autoregressive Transformer model with considerable speedup.
CoMoL: Efficient Mixture of LoRA Experts via Dynamic Core Space Merging (2026.findings-acl)

Copied to clipboard

Challenge: Existing PEFT methods suffer from limited parameter efficiency and coarse-grained adaptation due to proliferation of LoRA experts and instance-level routing.
Approach: They propose a new MoE-LoRA framework that incorporates expert diversity, parameter efficiency, and fine-grained adaptation.
Outcome: The proposed framework outperforms existing methods on multiple tasks while maintaining parameter efficiency.
GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI Agent (2025.acl-long)

Copied to clipboard

Challenge: GUI automation is a key challenge in dynamic environments.
Approach: They propose a training-free GUI agent that integrates two mechanisms to explore trajectories in GUIs.
Outcome: The proposed GUI-explorer shows significant improvements over existing agents.
MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem Solving (2022.findings-naacl)

Copied to clipboard

Challenge: Existing work on math word problem solvers replace real numbers with symbolic placeholders to focus on logic reasoning.
Approach: They propose to inject numerical properties into symbolic placeholders with contextualized representation learning schema to solve number representation dilemma.
Outcome: The proposed model can solve MWP problems on English and Chinese benchmarks.
Multi-Level Cross-Modal Alignment for Speech Relation Extraction (2024.emnlp-main)

Copied to clipboard

Challenge: Existing studies use synthetic speech to train and evaluate SpeechRE models, hindering their development . modality gap issue limits performance of existing models, limiting future researches .
Approach: They propose to use speech data to train and evaluate SpeechRE models by using real speech . they propose to train a cross-modal alignment model to bridge the modality gap .
Outcome: The proposed model can train to bridge the modality gap between speech encoder and text decoder . the proposed model is based on two real SpeechRE datasets .
Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Existing studies focus on pre-trained LLMs to better understand and improve their trustworthiness.
Approach: They apply linear probing to LLMs to explore five key dimensions of trustworthiness: reliability, privacy, toxicity, fairness, and robustness.
Outcome: The proposed model can distinguish concepts in each trustworthiness dimension, suggesting that it can be trained in early pre-training.
Understanding Jargon: Combining Extraction and Generation for Definition Modeling (2022.emnlp-main)

Copied to clipboard

Challenge: Existing methods for generating definitions of words/phrases perform poorly on jargon.
Approach: They propose to combine extraction and generation for jargon definition modeling by extracting definitional information from the Web and incorporating extracted definitional data.
Outcome: The proposed method outperforms state-of-the-art models significantly on jargon definitions.
Quantifying Association Capabilities of Large Language Models and Its Implications on Privacy Leakage (2024.findings-eacl)

Copied to clipboard

Challenge: a new study examines the association capabilities of large language models . as models scale up, their ability to associate entities/information intensifies . however, there is a performance gap when associating commonsense knowledge versus PII, with the latter showing lower accuracy.
Approach: They examine the association capabilities of large language models and identify factors that influence their proficiency in associating information.
Outcome: The proposed models show a performance gap when associating commonsense knowledge versus PII, with the latter showing lower accuracy.
Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization (2024.findings-acl)

Copied to clipboard

Challenge: Recent approaches to language model alignment assume homogeneous human preferences, but actual human preferences vary widely and are hard to satisfy with a single language model.
Approach: They propose an RL-free extension of Direct Preference Optimization (DPO) that folds language modeling directly into reward modeling and trains language models as collective reward models that combine all objectives with specific weights.
Outcome: The proposed method matches or outperforms existing methods in safety alignment and long-form question answering.
On Orthogonality Constraints for Transformers (2021.acl-short)

Copied to clipboard

Challenge: a dedicated study on orthogonality constraints for transformers has been lacking . plug-and-play constraints increase the BLEU of transformers .
Approach: They propose to use plug-and-play constraints to encourage matrices to be orthogonal for numerical stability.
Outcome: The proposed constraint increases the BLEU on the large-scale WMT’16 EnDe benchmark by a factor of 28.4 to 29.6.
CMDAG: A Chinese Metaphor Dataset with Annotated Grounds as CoT for Boosting Metaphor Generation (2024.lrec-main)

Copied to clipboard

Challenge: Metaphors are a prominent linguistic device in human language and literature, as they add color, imagery, and emphasis to enhance effective communication.
Approach: They propose a large-scale high quality annotated Chinese Metaphor Corpus . they use a set of guidelines to ensure the accuracy and consistency of their annotations .
Outcome: The proposed corpus generates metaphors that resonate more with real-world intuition.
Compositional Mathematical Encoding for Math Word Problems (2023.findings-acl)

Copied to clipboard

Challenge: Existing MWP encoders work in a unimodal setting and map problem description to latent representation, then for decoding.
Approach: They propose a Compositional Math Word Problem Solver which maps problem description to latent representation and decodes it in an interactive way.
Outcome: Extensive experiments show that the proposed model outperforms state-of-the-art models on public benchmarks.
Abstract then Play: A Skill-centric Reinforcement Learning Framework for Text-based Games (2023.findings-acl)

Copied to clipboard

Challenge: Existing reinforcement learning frameworks fail to decompose the task and abstract the action autonomously.
Approach: They propose a skill-centric reinforcement learning framework capable of abstracting the action in an end-to-end manner.
Outcome: Empirical experiments on the Jericho environment validate the proposed framework against state-of-the-art baselines.
Understanding and Addressing the Under-Translation Problem from the Perspective of Decoding Objective (2024.acl-long)

Copied to clipboard

Challenge: Neural Machine Translation (NMT) has made remarkable progress over the past years, but under-translation and over-translatation remain challenging obstacles faced by NMT systems.
Approach: They propose to employ the confidence of predicting the end of sentence (EOS) as a detector for under-translation and strengthen the confidence-based penalty to penalize candidates with a high risk of under-translated.
Outcome: The proposed method can detect and rectify under-translated outputs, with minor impact on other correct translations.
Graph-to-Tree Learning for Solving Math Word Problems (2020.acl-main)

Copied to clipboard

Challenge: Existing tree-based neural models do not capture the relationships and order information among the quantities well.
Approach: They propose a novel deep learning architecture that combines the merits of the graph-based encoder and tree-based decoder to generate better solution expressions.
Outcome: The proposed framework outperforms the state-of-the-art on two available datasets significantly.
Instruction Position Matters in Sequence Generation with Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) can perform conditional sequence generation tasks, such as translation or summarization, through instruction fine-tuning.
Approach: They propose to shift the position of task instructions after the input sentences to enhance the model's instruction-following capability.
Outcome: The proposed method outperforms traditional settings across various model scales (1B / 7B & 13B) and different sequence generation tasks (translation and summarization) without any additional data or annotation costs.
Diverse, Controllable, and Keyphrase-Aware: A Corpus and Method for News Multi-Headline Generation (2020.emnlp-main)

Copied to clipboard

Challenge: Existing methods for news headline generation focus on producing a single short sentence . et al., 2017; Gehrmann e.t., 2018; Zhong ee., 2019) focus on single-headline generation.
Approach: They propose a method to generate multiple headlines with keyphrases of user interests . they propose generating multiple keyphrase-relevant headlines using a transformer decoder .
Outcome: The proposed method achieves state-of-the-art in terms of quality and diversity.

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