Papers by Jiayu Zhou

7 papers
Dynamic Uncertainty Ranking: Enhancing Retrieval-Augmented In-Context Learning for Long-Tail Knowledge in LLMs (2025.naacl-long)

Copied to clipboard

Challenge: Prior work has shown that in-context learning (ICL) with retriever augmentation can help LLMs better capture long-tail knowledge, reducing their reliance on pre-trained data.
Approach: They propose a reinforcement learning-based dynamic uncertainty ranking method that accounts for the varying impact of each retrieved sample on LLM predictions.
Outcome: The proposed method outperforms baseline models on question-answering datasets by 2.76% and 5.96% on long-tail questions that elude zero-shot inference.
SEE: Signal Embedding Energy for Quantifying Noise Interference in Large Audio Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing studies on noise lack quantitative analysis and rely on intuition and empirical observation, thus failing to understand practical robustness.
Approach: They propose a method for quantifying the impact of noise intensity on LALM inputs by using a structured activation subspace derived from the model's internal representations.
Outcome: The proposed method outperforms existing denoising methods and demonstrates that noise is perceived more accurately than raw audio features.
Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for fine-tuning large language models fail due to performance degradation . existing methods fail for models fine- tuned with low-rank adaptation .
Approach: They propose to constrain the LoRA subspace prior to fine-tuning to ensure that updates relevant to one task do not adversely shift outputs for others.
Outcome: The proposed method can integrate with most existing merging algorithms, reducing unintended interference among tasks.
A Speaker-Aware Co-Attention Framework for Medical Dialogue Information Extraction (2022.emnlp-main)

Copied to clipboard

Challenge: With the development of medical digitization, the extraction and structuring of electronic medical records (EMRs) have become challenging but fundamental tasks.
Approach: They propose a speaker-aware dialogue encoder with multi-task learning which takes the speaker's identity into account and a co-attention fusion network to aggregate the utterance information.
Outcome: The proposed framework outperforms the state-of-the-art methods on the public medical dialogue extraction datasets to demonstrate its superiority.
Dual Debiasing for Noisy In-Context Learning for Text Generation (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods detect noisy annotations by ranking local perplexities, but this assumption breaks down when the noise ratio is high and many demonstrations are flawed.
Approach: They propose a method that uses synthesized neighbors to explicitly correct perplexity estimates, yielding a robust Sample Cleanliness Score.
Outcome: The proposed method is comparable to a fully clean demonstration corpus and performs well even with noise ratios as high as 0.8.
AscendKernelGen: LLM-Driven Kernel Generation for NPUs (2026.findings-acl)

Copied to clipboard

Challenge: Neural Processing Units (NPUs) are critical for AI infrastructure, but their development remains a bottleneck due to vendor-specific Domain-Specific Languages (DSLs).
Approach: They propose a framework for NPU kernel development that bridges the gap in hardware-specific coding . compiler success on complex Level-2 kernels improves from 0% to 95.5%, they say .
Outcome: The proposed framework bridges the gap in hardware-specific coding, showing a near-zero success rate on complex kernels.
Dynamic Augmentation Data Selection for Few-shot Text Classification (2022.findings-emnlp)

Copied to clipboard

Challenge: Data augmentation is a popular method for fine-tuning pre-trained language models to increase model robustness and performance.
Approach: They propose a dynamic data selection method to select effective augmentation data from different augmentation sources according to the model’s learning stage by identifying a set of augmentation samples that optimally facilitates the learning process of the most current model.
Outcome: The proposed method outperforms strong baselines on a variety of sentence classification tasks.

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