Papers by Yi-Ting Huang

4 papers
Neuron-Level Differentiation of Memorization and Generalization in Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Existing models exhibit memorization and generalization behaviors in ways that are not easily interpretable or controllable.
Approach: They propose to use a GPT-2 and LLaMA-3.2 model to identify distinct neuron subsets responsible for each behavior to steer the model toward memorization or generalization.
Outcome: The proposed models show that inference-time interventions on these neurons can steer the model’s behavior toward memorization or generalization.
Mixture of Ordered Scoring Experts for Cross-prompt Essay Trait Scoring (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches to automate essay scoring overlook critical information, authors say . evaluators often limit their performance to unseen topics, resulting in incomplete assessment perspectives.
Approach: They propose a framework that integrates information from prompts and essays into an AES framework.
Outcome: The proposed framework achieves state-of-the-art in cross-prompt scoring and multi-trait scoring on the ASAP++ dataset.
Dynamic Graph Transformer for Implicit Tag Recognition (2021.eacl-main)

Copied to clipboard

Challenge: Existing studies focus on using explicit information in articles and do not consider the implicit information.
Approach: They propose a dynamic graph transformer that distills the textual information and the entity relations on the fly.
Outcome: The proposed model can extract the textual information and the entity relations on the fly.
MPDD: A Multi-Party Dialogue Dataset for Analysis of Emotions and Interpersonal Relationships (2020.lrec-1)

Copied to clipboard

Challenge: Existing datasets with emotion and relation labels for dialogues are limited.
Approach: They use a Chinese dialogue dataset to annotate emotions and interpersonal relationships on each utterance.
Outcome: The proposed dataset contains 25,548 utterances from 4,142 dialogues.

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