Papers by Jianyi Zhang

5 papers
GLoCIM: Global-view Long Chain Interest Modeling for news recommendation (2025.coling-main)

Copied to clipboard

Challenge: Recent efforts to extract local subgraph information from click graphs have hindered collaboratively utilizing global click graph information.
Approach: They propose a global-view long chain interests model that models a click graph with neighbor interest to enhance news recommendation.
Outcome: The proposed method surpasses baseline methods on two real-world datasets.
Revisiting Block-based Quantisation: What is Important for Sub-8-bit LLM Inference? (2023.emnlp-main)

Copied to clipboard

Challenge: Existing quantisation methods mainly focus on 8-bit LLMs . a lack of scaling offsets in the quantisation process limits the use of LLM inference.
Approach: They propose to use block quantisations to reduce scaling offsets in Large language models . they find that the block quantizations reduce scaling only from an arithmetic perspective .
Outcome: The proposed methods reduce scaling offsets solely from an arithmetic perspective without additional treatments in the computational path.
Neuron Activation Modulation for Text Style Transfer: Guiding Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Text style transfer (TST) aims to flexibly adjust the style of text while preserving its core content.
Approach: They propose a method that aligns activation values of style-related neurons with those of the target style to guide the model in performing the transfer.
Outcome: The proposed method significantly improves style transfer quality while preserving core content.
Refining Salience-Aware Sparse Fine-Tuning Strategies for Language Models (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for fine-tuning large language models require expensive training on consumer-grade hardwares.
Approach: They propose a sparsity-based approach that introduces trainable sparse adaptations to the weight matrices in the model and offers greater flexibility in selecting fine-tuned parameters.
Outcome: The proposed method outperforms other methods for a simple yet effective baseline for nLP tasks while sacrificing performance.
ReAugKD: Retrieval-Augmented Knowledge Distillation For Pre-trained Language Models (2023.acl-short)

Copied to clipboard

Challenge: Knowledge distillation (KD) is an effective compression technique to derive a smaller student model from a larger teacher model by transferring the knowledge embedded in the teacher's network.
Approach: They propose a framework and loss function that preserves the semantic similarities of teacher and student training examples to enable the student to retrieve from the knowledge base effectively.
Outcome: The proposed framework preserves the semantic similarities of teacher and student training examples to achieve state-of-the-art performance on the GLUE benchmark.

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