Papers by Xiaofeng Zhou

10 papers
Debate, Reflect, and Distill: Multi-Agent Feedback with Tree-Structured Preference Optimization for Efficient Language Model Enhancement (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods for enhancing small models struggle to yield substantial and lasting performance gains.
Approach: They propose a Debate and Reflect framework that orchestrates multi-turn debates between smaller models and stronger teacher models.
Outcome: The proposed framework outperforms existing methods by a large margin in smaller models.
VarMAE: Pre-training of Variational Masked Autoencoder for Domain-adaptive Language Understanding (2022.findings-emnlp)

Copied to clipboard

Challenge: Pre-trained language models have been widely applied to standard benchmarks due to the limited resources available in a domain.
Approach: They propose a Transformer-based language model called VarMAE for domain-adaptive language understanding that encodes the context of a token into a smooth latent distribution.
Outcome: Experiments on science- and finance-domain NLU tasks show that the proposed model can be efficiently adapted to new domains with limited resources.
Fundamental Capabilities of Large Language Models and their Applications in Domain Scenarios: A Survey (2024.acl-long)

Copied to clipboard

Challenge: Existing benchmark-based evaluations cannot accurately reflect the performance of real-world applications.
Approach: They propose a reliable strategy for domains to choose more robust LLMs for real-world applications.
Outcome: The proposed strategy addresses the challenges faced by domains to choose more robust LLMs for real-world applications.
MirrorQA: Benchmarking Multimodal LLMs on Mirror-Orientation Reasoning (2026.acl-long)

Copied to clipboard

Challenge: Multimodal large language models (MLLMs) have achieved remarkable progress in recent years, yet their ability to perform left–right reasoning in mirror contexts remains underexplored.
Approach: They propose a benchmark to evaluate MLLMs' ability to distinguish left from right from a subject-centered perspective.
Outcome: The proposed benchmarks show that even the best performing models achieve only 65.40% accuracy, far below the 99.28% accuracy of humans.
ShieldHead: Decoding-time Safeguard for Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Recent advances in LLM-based moderation methods have demonstrated remarkable promise in identifying safety risks associated with both inputs and outputs in human-AI interactions.
Approach: They propose to learn a classification head on the last-layer hidden states of a dialogue model and use it to detect harmful content.
Outcome: The proposed framework is 300 faster (**1ms**) than previous LLM-based moderation models with 99% less parameters than LlamaGuard.
Mixture of Attention Heads: Selecting Attention Heads Per Token (2022.emnlp-main)

Copied to clipboard

Challenge: Mixture-of-Experts (MoE) networks have been proposed as an efficient way to scale up model capacity and implement conditional computing.
Approach: They propose a new architecture that combines multi-head attention with the MoE mechanism and a sparsely gated architecture that allows for faster computations.
Outcome: The proposed architecture can scale up the number of attention heads and the number parameters while preserving computational efficiency.
MoSLD: An Extremely Parameter-Efficient Mixture-of-Shared LoRAs for Multi-Task Learning (2025.coling-main)

Copied to clipboard

Challenge: LoRA is a key technique for fine-tuning large pre-trained models, yet its performance in multi-task learning scenarios often falls short.
Approach: They propose a mixture-of-shared-LoRAs model with a dropout strategy . they propose to share the upper projection matrix among different experts .
Outcome: The proposed model exhibits excellent performance in both single-task and multi-task scenarios with robust out-of-domain generalization capabilities.
WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback (2026.acl-long)

Copied to clipboard

Challenge: Traditional alignment methods rely on human annotations and are subjective and misalignment with real-world user preferences.
Approach: They propose a framework that leverages in-situ user feedback during conversations with LLMs to create preference datasets automatically.
Outcome: The proposed framework identifies and classifies user feedback to LLM responses between conversation turns and creates examples of preferred and dispreferred responses according to user preferences.
GenTool: Enhancing Tool Generalization in Language Models through Zero-to-One and Weak-to-Strong Simulation (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) can expand their capabilities by integrating external tools.
Approach: They propose a training framework that prepares LLMs for diverse generalization challenges in tool utilization.
Outcome: The proposed framework improves the tool-usage capabilities of LLMs by up to 8B parameters, surpassing GPT-4o.
SphereRE: Distinguishing Lexical Relations with Hyperspherical Relation Embeddings (P19-1)

Copied to clipboard

Challenge: Lexical relations are relations between terms in lexicons.
Approach: They propose a neural representation learning model to distinguish lexical relations among term pairs based on hyperspherical relation embeddings.
Outcome: The proposed model outperforms state-of-the-art models on several benchmarks.

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