Papers by Yao Meng

13 papers
ResoFilter: Fine-grained Synthetic Data Filtering for Large Language Models through Data-Parameter Resonance Analysis (2025.findings-naacl)

Copied to clipboard

Challenge: Existing methods for enhancing large language models lack clear metrics for evaluating data characteristics.
Approach: They propose a method that integrates models, data, and tasks to refine datasets.
Outcome: The proposed method achieves comparable results to full-scale fine-tuning using only half the data in mathematical tasks and exhibits strong generalization across different models and domains.
A Learning-Exploring Method to Generate Diverse Paraphrases with Multi-Objective Deep Reinforcement Learning (2020.coling-main)

Copied to clipboard

Challenge: Paraphrase generation is of great importance for many downstream tasks in natural language processing.
Approach: They propose a method to generate sentences as learning objectives from the learned data distribution and employ reinforcement learning to combine these new learning objectives for model training.
Outcome: The proposed method gains significant diversity and improves generation quality over state-of-the-art datasets.
Balanced Joint Adversarial Training for Robust Intent Detection and Slot Filling (2020.coling-main)

Copied to clipboard

Challenge: Existing joint models for intent detection and slot filling show insufficient robustness . however, some small changes of inputs can fool the models to produce wrong predictions .
Approach: They propose a joint adversarial training model that generates adversarials to attack the joint model and trains the model to defend against the adversarial examples.
Outcome: The proposed model achieves significantly higher scores and improves robustness on two datasets.
Syntactically-Informed Unsupervised Paraphrasing with Non-Parallel Data (2021.emnlp-main)

Copied to clipboard

Challenge: Existing studies on syntactically controlled paraphrase generation rely on large-scale parallel data.
Approach: They propose a syntactically-informed unsupervised paraphrasing model based on conditional variational auto-encoder which can generate texts in a specified syntastic structure.
Outcome: The proposed model can generate diverse paraphrases with specified syntactic structure using non-parallel data.
Personality Understanding of Fictional Characters during Book Reading (2023.acl-long)

Copied to clipboard

Challenge: Existing methods to predict characters' personalities have not been studied in the NLP field due to the lack of appropriate datasets mimicking the process of book reading.
Approach: They propose a dataset to predict characters' personalities that uses an exhaustive vocabulary of personality traits as targets.
Outcome: The proposed dataset is efficient and accurate and relies on long-term context to achieve accurate predictions for both machines and humans.
Don’t Eclipse Your Arts Due to Small Discrepancies: Boundary Repositioning with a Pointer Network for Aspect Extraction (2020.acl-main)

Copied to clipboard

Challenge: Existing aspect extraction methods suffer from boundary errors, but they hurt performance severely.
Approach: They propose to use a pointer network to reposition the boundaries of extracted aspects . they conduct experiments on laptop and restaurant benchmark datasets .
Outcome: The proposed method outperforms state-of-the-art methods on benchmark datasets . it achieves substantial improvements over baseline and outperformed existing methods .
From Discrimination to Generation: Low-Resource Intent Detection with Language Model Instruction Tuning (2024.findings-acl)

Copied to clipboard

Challenge: Existing studies fine-tune discriminative models on specific defined intent classes, preventing them from being directly adopted to new intent domains.
Approach: They propose to use a pre-trained generative intent model to detect new intents from different domains with no parameter updates.
Outcome: The proposed model outperforms baselines that need further fine-tuning or domain-specific samples.
Improving Graph-based Sentence Ordering with Iteratively Predicted Pairwise Orderings (2021.emnlp-main)

Copied to clipboard

Challenge: Existing sentence ordering models can be classified into pairwise ordering models and set-to-sequence models.
Approach: They propose a novel sentence ordering framework which introduces two classifiers to make better use of pairwise orderings for graph-based sentence ordering.
Outcome: The proposed model achieves state-of-the-art performance on five commonly-used datasets.
Speaking in Wavelet Domain: A Simple and Efficient Approach to Speed up Speech Diffusion Model (2024.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to enhance inference speed and training require complex modifications to the model.
Approach: They propose to double the training and inference speed of Denoising Diffusion Probabilistic Models by simply redirecting the generative target to the wavelet domain.
Outcome: The proposed method doubles the training and inference speed of Speech DDPMs by redirecting the generative target to the wavelet domain.
Clear Up Confusion: Iterative Differential Generation for Fine-grained Intent Detection with Contrastive Feedback (2025.coling-main)

Copied to clipboard

Challenge: Recent studies on fine-grained intent detection have focused on collecting large-scale and high-quality samples via crowdsourcing resulting in data scarcity.
Approach: They propose an iterative differential generation framework with contrastive feedback to generate high-quality pseudo samples and accurately capture the crucial nuances in target class distribution.
Outcome: The proposed framework generates high-quality pseudo samples and captures crucial nuances in target class distribution.
AlphaQT-Bench: Diagnosing the Gap between Financial Code Generation and Quantitative Reasoning in LLMs (2026.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks rely on outcome-driven metrics such as profitability and look-ahead bias.
Approach: They propose a diagnostic benchmark for instruction-grounded financial code generation under strict semantic and temporal constraints.
Outcome: The proposed benchmarks show that the models fail under causal, structural, or functional constraints.
Towards Better Value Principles for Large Language Model Alignment: A Systematic Evaluation and Enhancement (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) show remarkable performance across tasks . alignment with human values is critical for their responsible development.
Approach: They propose a framework that evaluates value principles along three desirable properties . they propose supervised fine-tuning, reinforcement learning-based approaches .
Outcome: The proposed framework improves value principles along the three desirable properties of LLMs.
Learning Structural Information for Syntax-Controlled Paraphrase Generation (2022.findings-naacl)

Copied to clipboard

Challenge: Syntax-controlled paraphrase generation aims to produce paraphrase conform to given syntactic patterns.
Approach: They propose a model that captures parent-child and sibling relations and a syntax encoder to capture alignment relations.
Outcome: The proposed model achieves state-of-the-art in terms of semantic and syntactic quality on two popular benchmark datasets.

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