Papers by Yi-Ting Huang
Neuron-Level Differentiation of Memorization and Generalization in Large Language Models (2025.emnlp-main)
Copied to clipboard
Ko-Wei Huang, Yi-Fu Fu, Ching-Yu Tsai, Yu-Chieh Tu, Tzu-ling Cheng, Cheng-Yu Lin, Yi-Ting Yang, Heng-Yi Liu, Keng-Te Liao, Da-Cheng Juan, Shou-De Lin
| 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. |