Papers by Xiaoyuan Zhu

5 papers
Using Linguistic Entrainment to Evaluate Large Language Models for Use in Cognitive Behavioral Therapy (2025.findings-naacl)

Copied to clipboard

Challenge: Entrainment is a communication process that builds a strong relationship between a mental health therapist and their client.
Approach: They evaluate the linguistic entrainment of an LLM in a mental health dialog setting and compare it to trained therapists and non-expert online peer supporters.
Outcome: The proposed model outperforms humans in a cognitive behavioral therapy setting.
TS-CLIP: Time Series Understanding by CLIP (2025.emnlp-main)

Copied to clipboard

Challenge: Contrastive Language–Image Pre-training (CLIP) has demonstrated remarkable success in aligning vision and language.
Approach: They propose a synonym bank mechanism that generates synonym embeddings as alignment targets.
Outcome: The proposed approach achieves state-of-the-art (SOTA) performance on 51 datasets.
Can LLMs Understand Unvoiced Speech? Exploring EMG-to-Text Conversion with LLMs (2025.acl-short)

Copied to clipboard

Challenge: Unvoiced electromyography (EMG) is an effective communication tool for individuals unable to produce vocal speech.
Approach: They propose an EMG adaptor module that maps EMG features to an LLM's input space and achieves an average word error rate of 0.49 on a closed-vocabulary unvoiced EMG-to-text task.
Outcome: The proposed module achieves an average word error rate of 0.49 on a closed-vocabulary unvoiced EMG-to-text task.
Enhancing LLM-Based Social Bot via an Adversarial Learning Framework (2025.emnlp-main)

Copied to clipboard

Challenge: Social media platforms provide an ideal testbed for large language models that exhibit human-like behavior.
Approach: They propose an LLM-based social **Bot that enhances human-like generative capabilities through an adversarial learning framework.
Outcome: The proposed framework generates human-like content aligned with diverse user profiles . it exhibits strong social responsiveness, more accurately modeling opinion dynamics .
Learn Your Tokens: Word-Pooled Tokenization for Language Modeling (2023.findings-emnlp)

Copied to clipboard

Challenge: Language models typically tokenize text into subwords, using a deterministic, hand-engineered heuristic of combining characters into longer surface-level strings such as ‘ing’ or whole words.
Approach: They propose a 'learn your tokens' scheme which pooles bytes/characters into word representations and decodes individual characters/bytes per word in parallel.
Outcome: The proposed tokenizer outperforms subword models and byte/character models over the word boundary and outperformed on rare words by a factor of 30!

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