Papers by Haiqin Yang

12 papers
A Unified One-Step Solution for Aspect Sentiment Quad Prediction (2023.findings-acl)

Copied to clipboard

Challenge: Existing ASQP datasets are small and low-density, hindering technical advancement . et al. (2017): aspect sentiment quad prediction provides a complete aspect-level sentiment structure.
Approach: They propose a one-step solution for Aspect sentiment quad prediction that can detect aspect categories and identify aspectopinion-sentiment triplets simultaneously.
Outcome: The proposed solution can detect aspect categories and identify aspectopinion-sentiment triplets simultaneously.
Intrinsic Test of Unlearning Using Parametric Knowledge Traces (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for “unlearning” information captured in large language models rely on behavioral tests without monitoring residual knowledge in model parameters.
Approach: They propose a general evaluation methodology that uses vocabulary projections to inspect concepts encoded in model parameters.
Outcome: The proposed method detects changes in parametric traces of unlearned concepts and localizes them in two open-source LLMs.
A Two-Agent Game for Zero-shot Relation Triplet Extraction (2024.findings-acl)

Copied to clipboard

Challenge: Existing methods for relation triplet extraction rely on labeled data and are limited in their applicability.
Approach: They propose a two-agent game approach to deliberate and debate unseen relations by two agents, a generator and an extractor.
Outcome: The proposed method outperforms baseline methods by 6%-16% in F1 scores.
A Diffusion Model for Event Skeleton Generation (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods for event schema generation are noise-sensitive and error-accumulating, e.g., inability to correct errors while generating schema.
Approach: They propose a novel diffusion event graph model that embeds and roundes event graphs into learnable latent representations and a denoising process to maintain the model's robustness.
Outcome: The proposed model achieves better results than existing state-of-the-art models on three IED bombing datasets.
Task-wrapped Continual Learning in Task-Oriented Dialogue Systems (2025.findings-naacl)

Copied to clipboard

Challenge: Continual learning is vital for task-oriented dialogue systems (ToDs), but its performance is limited by training separate adapters for each task, preventing global knowledge sharing.
Approach: They propose a framework that employs task-wrapped Adapters to learn global and task-specific information through parameter sharing.
Outcome: The proposed framework outperforms AdapterCL in 37 domains while using only 46% of the parameters.
Sparse Adapter Fusion for Continual Learning in NLP (2026.eacl-long)

Copied to clipboard

Challenge: Existing methods for learning continuously face challenges such as inefficient parameter reuse across tasks and catastrophic forgetting when tasks are dissimilar.
Approach: They propose a Sparse Adapter Fusion Method which dynamically fuses old and new adapters to address these challenges.
Outcome: The proposed method outperforms state-of-the-art methods while utilizing less than 60% of the parameters.
Let’s Play Across Cultures: A Large Multilingual, Multicultural Benchmark for Assessing Language Models’ Understanding of Sports (2025.emnlp-main)

Copied to clipboard

Challenge: Language Models (LMs) are primarily evaluated on globally popular sports, often overlooking regional and indigenous sporting traditions.
Approach: They propose to use multiple-choice questions (MCQs) to assess LMs' understanding of traditional sports across 60 countries and 6 continents.
Outcome: The new benchmark will be publicly available, fostering research in culturally aware AI systems.
Beyond Prompt Engineering: A Systematic Analysis of Prompt Lexical Sensitivity and Its Impacts on Quality (2026.findings-acl)

Copied to clipboard

Challenge: Existing studies on prompt engineering have focused on optimizing models for performance under stylistic perturbations.
Approach: They conduct the first analysis of n-gram token-level mechanisms . they find that higher average performance is inherently associated with lower variance and greater stability.
Outcome: The proposed model reduces the variance of the generated code by 40% . the proposed model is based on a large-scale dataset of 132,000 prompt variants .
ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQL (2026.acl-long)

Copied to clipboard

Challenge: Current Text-to-SQL reasoning models lack integrated execution feedback during generation.
Approach: They propose a text-to-SQL framework that interacts with the SQL execution engine during decoding and dynamically adjusts reasoning based on execution feedback.
Outcome: The proposed framework achieves 89.1% accuracy on Spider and 65.3% on BIRD at the 7B scale.
Dissecting Fine-Tuning Unlearning in Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for fine-tuning-based unlearning are ineffective at completely erasing model-embedded knowledge, but their true effectiveness remains unclear.
Approach: They propose to use activation patching and parameter restoration experiments to examine the limitations of fine-tuning-based unlearning methods for erasing harmful, sensitive, or copyrighted information within large language models.
Outcome: The proposed methods alter the model’s knowledge retrieval process rather than genuinely erasing the problematic knowledge embedded in the model parameters.
PARSQL: Enhancing Text-to-SQL through SQL Parsing and Reasoning (2025.findings-acl)

Copied to clipboard

Challenge: Large language models have made significant strides in text-to-SQL tasks, but small language models struggle to accurately interpret natural language questions due to resource limitations.
Approach: They propose a SQL parser that extracts constraints from SQL to generate sub-SQLs . they use a rule-based and LLM-based method to generate step-by-step SQL explanations based on the results .
Outcome: The proposed framework outperforms models with the same model size on BIRD and Spider benchmarks.
HiGRU: Hierarchical Gated Recurrent Units for Utterance-Level Emotion Recognition (N19-1)

Copied to clipboard

Challenge: Using textual features, our proposed HiGRU models achieve at least 8.7%, 7.5%, 6.0% improvement over the state-of-the-art methods on each dataset.
Approach: They propose a hierarchical gated recurrent unit framework to model word-level inputs and an upper-level GRU to capture contexts of utterance-level embeddings.
Outcome: The proposed framework achieves 8.7%, 7.5%, 6.0% improvement over state-of-the-art methods on three 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