Papers by Minghao Zhu

6 papers
Tracking Life’s Ups and Downs: Mining Life Events from Social Media Posts for Mental Health Analysis (2025.acl-long)

Copied to clipboard

Challenge: Existing studies have indicated that major life events can greatly impact individuals’ mental health, but shedding its light on social media data is challenging due to the complexity and ambiguity nature of life events.
Approach: They propose to extract life events mentioned in posts on social media to uncover a social media event dataset which includes 12 major life event categories that are likely to occur in everyday life.
Outcome: The proposed dataset includes 12 life event categories that are likely to occur in everyday life and is human-annotated under iterative procedure and boasts a high level of quality.
Marco-Bench-MIF: On Multilingual Instruction-Following Capability of Large Language (2025.acl-long)

Copied to clipboard

Challenge: Existing datasets for instruction-following are monolingual and centered on English . existing data are unable to capture linguistic and cultural subtle differences .
Approach: They propose an extension of IFEval to a localized multilingual version called Marco-Bench-MIF . their benchmark addresses linguistic constraints and cultural references via translation and verification .
Outcome: The proposed extension of IFEval to a localized multilingual version covers 30 languages with varying levels of localization.
StratMem-Bench: Evaluating Strategic Memory Use in Virtual Character Conversation Beyond Factual Recall (2026.acl-long)

Copied to clipboard

Challenge: Current benchmarks for memory utilization ignore this nuance, treating memory as a static repository of facts rather than a dynamic resource to be strategically deployed in character-centric dialogues.
Approach: They propose a benchmark to evaluate strategic memory use in character-centric dialogues . they use a dataset of 657 instances where virtual characters must navigate heterogeneous memory pools .
Outcome: The proposed benchmarks show that all models perform well at distinguishing between required and irrelevant memories, but struggle once supportive memories are introduced into the decision process.
TwinVoice: A Multi-dimensional Benchmark Towards Digital Twins via LLM Persona Simulation (2026.findings-acl)

Copied to clipboard

Challenge: Existing studies show that advanced LLMs produce text indistinguishable from human writing.
Approach: They propose a benchmark to assess persona simulation across diverse contexts by decomposing the evaluation into six fundamental capabilities including opinion consistency, memory recall, logical reasoning, persona tone, and syntactic style.
Outcome: The proposed model achieves moderate accuracy but falls short of the basic capabilities needed to simulate personas in real-world contexts.
Non-Autoregressive Neural Machine Translation with Consistency Regularization Optimized Variational Framework (2022.naacl-main)

Copied to clipboard

Challenge: Variational Autoencoder (VAE) is an effective framework to model the interdependency for non-autoregressive neural machine translation (NAT).
Approach: They propose to use Variational Autoencoder to model interdependency for non-autoregressive neural machine translation (NAT) a posterior consistency regularization approach is proposed to improve translation quality .
Outcome: The proposed model is 1.5/0.7 and 0.8/0.3 BLEU points faster than the baseline model.
Mapping Long-term Causalities in Psychiatric Symptomatology and Life Events from Social Media (2024.naacl-long)

Copied to clipboard

Challenge: Existing studies focus on the semantic content of social media posts, overlooking the evolving nature of mental disorders and symptoms.
Approach: They extract causality between psychiatric symptoms and life events from social media posts and extract temporal attributes to improve diagnosis and treatment planning.
Outcome: The extracted causality features improve diagnostic and treatment planning and improve performance in tasks such as depression and diagnosis point detection.

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