Papers by Xinyi Zhu

9 papers
SILO-BENCH: A Scalable Environment for Evaluating Distributed Coordination in Multi-Agent LLM Systems (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks conflate coordination ability with role-based priors.
Approach: They propose a role-free benchmark for evaluating free-form collaboration under information silos.
Outcome: The proposed benchmark systematically probes coordination capabilities under information silos using 54 configurations and 3 frontier LLMs.
MentalSeek-Dx: Towards Progressive Hypothetico-Deductive Reasoning for Real-world Psychiatric Diagnosis (2026.acl-long)

Copied to clipboard

Challenge: Mental health disorders represent a burgeoning global public health challenge . lack of ecological validity and fine-grained diagnostic supervision limits their utility .
Approach: They propose a medical-specialized LLM trained to internalize clinical reasoning process through supervised trajectory construction and curriculum-based reinforcement learning.
Outcome: The proposed model achieves state-of-the-art with only 14B parameters, establishing a clinically grounded framework for reliable psychiatric diagnosis.
CAGK: Collaborative Aspect Graph Enhanced Knowledge-based Recommendation (2024.lrec-main)

Copied to clipboard

Challenge: Existing KG-based recommendations have low link rates, redundant knowledge in KG, and low ratings and negative aspect sentiment.
Approach: They propose a model that integrates auxiliary information such as social networks, user or item attributes, images, contextual data, etc.
Outcome: The proposed model improves on two widely used benchmark datasets, Amazon-book and Yelp2018.
ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflection (2025.findings-acl)

Copied to clipboard

Challenge: ReflectEvo-460k is a large-scale, comprehensive, self-generated reflection dataset with broadened instructions and diverse multi-domain tasks.
Approach: They propose a pipeline that iteratively generates self-reflection for self-training and a large-scale reflection dataset with broadened instructions and diverse multi-domain tasks.
Outcome: The proposed pipeline improves Llama-3 reasoning ability by up to 71.2% and Mistral by upto 44.4%.
Code over Words: Overcoming Semantic Inertia via Code-Grounded Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models struggle with semantic inertia, a problem that is often attributed to natural language encoding, which entangles descriptive semantics and logical rules, leading to persistent hallucinations of familiar physics despite explicit contradictory rules.
Approach: They propose a framework that decouples logical dynamics from visual priors via amortized theory induction and counterfactual contrastive alignment.
Outcome: The proposed framework outperforms expensive inference-time search methods in both efficiency and accuracy.
PersLEARN: Research Training through the Lens of Perspective Cultivation (2023.acl-demo)

Copied to clipboard

Challenge: PersLEARN is a tool designed to facilitate the cultivation of scientific perspectives . junior researchers struggle to identify the perspectives reflected in the literature and struggle to develop their own viewpoints.
Approach: They propose a tool to facilitate the cultivation of scientific perspectives by interacting with a prompt-based model and allowing students to develop their own perspectives explicitly.
Outcome: The proposed tool outperforms baseline approaches across multiple domains of literature from different perspectives.
Mem2Evolve: Towards Self-Evolving Agents via Co-Evolutionary Capability Expansion and Experience Distillation (2026.acl-long)

Copied to clipboard

Challenge: Existing frameworks that focus on static tools and static assets are ineffective for self-evolving agents.
Approach: They propose a paradigm of co-evolutionary Capability Expansion and Experience Distillation that leverages accumulated experience to guide dynamic creation of assets.
Outcome: The proposed framework improves performance in single-task and cross-task settings by 18.53% over standard LLMs, 11.80% over agents evolving solely through experience, and 6.46% over those evolving solelly through asset creation.
Collaborative Generative AI: Integrating GPT-k for Efficient Editing in Text-to-Image Generation (2023.emnlp-main)

Copied to clipboard

Challenge: Experimental results show that GPT-k models focus more on inserting modifiers than predicting spontaneous changes in the primary subject matter.
Approach: They compare the common edits made by humans and GPT-k models to examine their performance in prompting T2I.
Outcome: The proposed models improve the prompt editing process by 20-30%, the authors show . they show that humans tend to replace words and phrases with modifiers .
SaCa: A Highly Compatible Reinforcing Framework for Knowledge Graph Embedding via Structural Pattern Contrast (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing knowledge Graph Embedding approaches lack structural semantics of knowledge graphs . structure-aware calibration (SaCa) is a framework designed to calibrate KGEs based on global structural patterns.
Approach: a new framework is designed to calibrate knowledge graphs using global structural patterns.
Outcome: a new framework can calibrate KGE models using global structural patterns . the framework consistently boosts performance across ten models on link prediction and entity classification tasks .

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