Papers by Cuiyun Gao
Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for reinforcement learning with verifiable rewards (RLVR) rely on static objective functions and rigid clipping strategies that misalign with the model’s evolving reasoning capabilities. |
| Approach: | They propose to incorporate Power-Mean Policy Optimization (PMPO) and Feedback-Adaptive Clipping (FAC) to overcome limitations of static mechanisms. |
| Outcome: | Extensive experiments on nine reasoning tasks show the proposed paradigm outperforms state-of-the-art methods. |
Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Existing unsupervised reinforcement learning methods lack the capacity to adapt to the model’s evolving reasoning capabilities during training. |
| Approach: | They propose an unsupervised reinforcement learning algorithm that adapts rewards to balance consensus and exploration based on the Free Energy Principle. |
| Outcome: | Empirical evaluations on nine datasets show that FREIA outperforms baseline methods on reasoning tasks. |
Enhancing Text-to-SQL Parsing through Question Rewriting and Execution-Guided Refinement (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing prompt engineering methods exploit database content and execution feedback to improve text-to-sql performance. |
| Approach: | They propose a framework for large language model-based text-to-sql task that exploits database content and execution feedback to improve execution accuracy. |
| Outcome: | The proposed framework improves execution accuracy and usability by 12.41% and 5.38% on four widely used benchmarks. |
A Survey on Natural Language Processing for Programming (2024.lrec-main)
Copied to clipboard
| Challenge: | Natural language processing for programming is a field of NLP and software engineering . it is used to assist programming, and is increasingly prevalent for its effectiveness in improving productivity. |
| Approach: | They propose to use NLP techniques to assist programming by obtaining a structure-based representation and a functionality-oriented algorithm. |
| Outcome: | The proposed approach could relieve developers from laborious work while improving efficiency for non-professional users. |
Affective Knowledge Enhanced Multiple-Graph Fusion Networks for Aspect-based Sentiment Analysis (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for sentiment analysis ignore the roles of syntax dependency relation labels and affective semantic information in determining the sentiment polarity of social media users. |
| Approach: | They propose a new multi-graph fusion network to leverage the richer syntax dependency relation labels and affective semantic information of words. |
| Outcome: | The proposed model outperforms state-of-the-art methods on three datasets. |
XMoE: Sparse Models with Fine-grained and Adaptive Expert Selection (2024.findings-acl)
Copied to clipboard
| Challenge: | XMoE leverages small experts and a threshold-based router to selectively engage only essential parameters. |
| Approach: | They propose a novel MoE that leverages small experts to selectively engage only essential parameters. |
| Outcome: | The proposed model can reduce computation load at MoE layers by over 50% without sacrificing performance. |
Split and Merge: Aligning Position Biases in LLM-based Evaluators (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have shown promise as automated evaluators for assessing the quality of answers generated by AI systems. |
| Approach: | They propose an alignment-based system that calibrates position bias in a lightweight yet effective manner by taking into account both length and semantics and combining them into a single prompt. |
| Outcome: | Extensive experiments with six LLMs on 11,520 answer pairs show that PORTIA significantly improves consistency and consistency rates with humans. |
Topic Memory Networks for Short Text Classification (D18-1)
Copied to clipboard
| Challenge: | Existing classification models for short texts are weak due to data sparsity . |
| Approach: | They propose topic memory networks for short text classification with a novel topic memory mechanism to encode latent topic representations indicative of class labels. |
| Outcome: | The proposed model outperforms state-of-the-art models on short text classification, while generating coherent topics. |
Boosting Vulnerability Detection of LLMs via Curriculum Preference Optimization with Synthetic Reasoning Data (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are capable of detecting software vulnerabilities, but lack of reasoning data hinders their ability to capture underlying vulnerability patterns. |
| Approach: | They propose a framework that excels at mining vulnerability patterns through reasoning data synthesizing and vulnerability-specific preference optimization. |
| Outcome: | The proposed framework improves on SVEN and PrimeVul datasets and improves 12.24%-22.77% accuracy. |
Once is Enough: A Light-Weight Cross-Attention for Fast Sentence Pair Modeling (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies suggest that transformer-based models perform cross-attention over input pairs, leading to computational cost. |
| Approach: | They propose a lightweight cross-attention mechanism that performs query encoding only once while modeling the query-candidate interaction in parallel. |
| Outcome: | The proposed model speeds up sentence pairing by over 113x while achieving comparable performance as the more expensive models. |