Papers by Yi Liao

8 papers
Mitigating Contradictions in Dialogue Based on Contrastive Learning (2022.findings-acl)

Copied to clipboard

Challenge: Current chatbots generate fluent, informative responses but sometimes generate contradictory responses when interacting with human.
Approach: They propose to use contrastive learning technique to mitigate contradiction issues in chatbots by minimizing the similarity between the target response and contradiction related negative example.
Outcome: The proposed method outperforms existing methods on automatic and human evaluation while preserving response fluency.
Probabilistically Masked Language Model Capable of Autoregressive Generation in Arbitrary Word Order (2020.acl-main)

Copied to clipboard

Challenge: Large-scale pretrained language models such as masked language model (MLM) have brought significant improvements to many NLU and NLG tasks.
Approach: They propose a probabilistic masking scheme for the masked language model and a model with a uniform prior distribution on the masking ratio.
Outcome: The proposed model outperforms BERT on a bunch of downstream NLG tasks.
A Global Past-Future Early Exit Method for Accelerating Inference of Pre-trained Language Models (2021.naacl-main)

Copied to clipboard

Challenge: Existing methods to accelerate inference speed of pre-trained language models are limited to local representations of exit layer . current models are associated with large memory requirement and high computational cost, which slow down inference and further encumber the application of PLMs.
Approach: They propose a method to exit early without passing through all inference layers . they take into consideration all the linguistic information embedded in the past layers a global perspective .
Outcome: The proposed method outperforms existing methods by a large margin . it uses linguistic information embedded in the past layers and future features . the proposed method is scalable and cost-effective .
NL ⇒ Schedule: Evaluate Multitask Scheduling Capability of Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for scheduling from natural language descriptions rely on experts with limited scheduling skills and domain knowledge.
Approach: They propose a model to generate a feasible schedule from natural language descriptions.
Outcome: The proposed framework achieves more robust performance than six state-of-the-art LLM+solver methods.
SoftDedup: an Efficient Data Reweighting Method for Speeding Up Language Model Pre-training (2024.acl-long)

Copied to clipboard

Challenge: Current methods focus on detecting and removing duplicates, which risks the loss of valuable information and neglects the varying degrees of duplication.
Approach: They propose a method that maintains dataset integrity while selectively reducing the sampling weight of data with high commonness.
Outcome: The proposed method significantly improves training efficiency on deduplicated datasets and improves downstream accuracy by 1.77%.
TGEA: An Error-Annotated Dataset and Benchmark Tasks for TextGeneration from Pretrained Language Models (2021.acl-long)

Copied to clipboard

Challenge: Using pretrained language models, we propose an error-annotated dataset for text generation . we use carefully selected prompt words to guide GPT-2 to generate candidate sentences .
Approach: They propose an error-annotated dataset with multiple benchmark tasks for text generation from pretrained language models.
Outcome: The proposed dataset covers 24 types of errors according to common sense and linguistics.
Exploring and Distilling Multi-Dimensional Clues for Interpretable Social Bot Detection (2026.acl-long)

Copied to clipboard

Challenge: Existing research on social bot detection results directly without corresponding supportive explanations, making it difficult to assess the extent to which such predictions are trustworthy.
Approach: They propose a four-dimensional clue framework that uses outcome-reward reinforcement learning to train inspectors to generate faithful, grounded clues from user information, semantic features, interactive situation, and behavioral pattern.
Outcome: The proposed framework outperforms baselines in detection performance and significantly improves the performance of large language models.
QuaSE: Sequence Editing under Quantifiable Guidance (D18-1)

Copied to clipboard

Challenge: Existing methods for Quantifiable Sequence Editing (QuaSE) require editing an input sequence to generate an output that satisfies a numerical outcome value measuring a certain property of the sequence.
Approach: They propose a framework for Quantifiable Sequence Editing that allows editing an input sequence to change an outcome and keep the content.
Outcome: The proposed framework disentangles outcome factor and content factor from the input sentence to allow editing to change the outcome and keep the content.

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