Papers by Xinyang Zhang

12 papers
Patton: Language Model Pretraining on Text-Rich Networks (2023.acl-long)

Copied to clipboard

Challenge: Existing models for text-rich networks do not take inter-document structure into account.
Approach: They propose a pretraining framework for a text-rich network using a masked language model and a masking node prediction framework.
Outcome: The proposed model outperforms baselines on four tasks in academic and e-commerce domains.
Mitigating Lost in Multi-turn Conversation via Curriculum RL with Verifiable Accuracy and Abstention Rewards (2026.acl-long)

Copied to clipboard

Challenge: Large Language Models exhibit strong capabilities in single-turn instruction following but suffer from Lost-in-Conversation (LiC) when instructions are revealed progressively in multi-turn settings, models get "Lost in Conversation"
Approach: They propose a framework that encourages models to generate correct answers and judge solvability in multi-turn conversations.
Outcome: The proposed framework improves models' ability to balance problem-solving with abstention . it reduces premature answering behaviors that cause lost-in-conversation (LiC)
Leveraging LLM Reasoning Enhances Personalized Recommender Systems (2024.findings-acl)

Copied to clipboard

Challenge: Recent advances have showcased the potential of Large Language Models (LLMs) in executing reasoning tasks, particularly facilitated by Chain-of-Thought (CoT) prompting.
Approach: They propose to use Large Language Models to perform tasks with subjectivity and personalized preferences as inputs to RecSys.
Outcome: The proposed framework aligns with real human judgment on the coherence and faithfulness of LLM reasoning responses.
Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs (2025.acl-long)

Copied to clipboard

Challenge: Existing role-play fine-tuning techniques improve role adaptability but may degrade safety performance, especially for villainous characters.
Approach: They propose safety-aware Role-Play Fine-Tuning (SaRFT) to balance role-playing capabilities and safety.
Outcome: The proposed method outperforms state-of-the-art baselines under both LoRA and full-parameter fine-tuning settings.
ALERT: An LLM-powered Benchmark for Automatic Evaluation of Recommendation Explanations (2025.naacl-long)

Copied to clipboard

Challenge: Existing benchmarks for recommendation explanation evaluation lack item diversity and user preferences data.
Approach: They propose a model-agnostic recommendation explanation evaluation benchmark based on Amazon e-commerce categories with implicit preferences . they propose two novel automatic evaluators that enable scalable and human-preference aligned evaluation of explanations .
Outcome: The proposed model-agnostic evaluation benchmark outperforms existing methods in a variety of domains.
META: Metadata-Empowered Weak Supervision for Text Classification (2020.emnlp-main)

Copied to clipboard

Challenge: Existing methods for weakly supervised text classification use text data alone to generate pseudo-labels . strong label indicators exist in metadata and it has been long overlooked due to challenges .
Approach: They propose a framework that leverages metadata as an additional source of weak supervision by combining text data and metadata into a text-rich network.
Outcome: The proposed framework exploits metadata as an additional source of weak supervision.
A Multilingual Dataset and Empirical Validation for the Mutual Reinforcement Effect in Information Extraction (2026.findings-acl)

Copied to clipboard

Challenge: Existing work on the Mutual Reinforcement Effect in information extraction has not been empirically validated . 76 percent of the 21 sub-datasets exhibit the Mutual Reforcement effect across languages .
Approach: They propose a multilingual MRE mix dataset that integrates 21 sub-datasets covering English, Japanese, and Chinese.
Outcome: The proposed framework reduces manual annotation effort while preserving structural requirements of MRE tasks.
DORM: Preference Data Weights Optimization for Reward Modeling in LLM Alignment (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to align large language models with human preferences are noisy and varying in importance of preference samples.
Approach: a new method enhances reward modeling by learning to dynamically weigh preference data.
Outcome: a new method improves the performance of large language models with human preferences . it initializes data importance and iteratively refines them to maximize validation performance.
SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive Thinking (2026.acl-long)

Copied to clipboard

Challenge: Large Reasoning Models (LRMs) produce excessively long Chains of Thought (COT) Existing solutions that improve token efficiency but sacrifice fine-grained control can disrupt the logical integrity of the reasoning process.
Approach: They propose a framework that performs step-level, difficulty-aware pruning while preserving the core reasoning structure.
Outcome: Experiments show that SAT reduces reasoning tokens by 40% while maintaining or improving accuracy.
MGR: Multi-generator Based Rationalization (2023.acl-long)

Copied to clipboard

Challenge: Existing approaches to explain NLP models have two key challenges: spurious correlation and degeneration.
Approach: They propose a rationalization framework using a generator and a predictor to construct a self-explaining NLP model with spurious correlation and degeneration as key challenges.
Outcome: The proposed method improves the F1 score by 20.9% compared to state-of-the-art methods.
AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender (2025.emnlp-main)

Copied to clipboard

Challenge: Activation steering offers training-free defense but relies on fixed steering coefficients, resulting in suboptimal protection and increased false rejections of benign inputs.
Approach: They propose an adaptive activation steering method that dynamically adjusts model behavior based on input characteristics.
Outcome: The proposed method outperforms baseline methods across multiple jailbreak attacks with minimal impact on utility.
PersonaAgent: Bridging Memory and Action for Personalized LLM Agents (2026.findings-acl)

Copied to clipboard

Challenge: Existing Large Language Model (LLM) enabled agents lack flexibility to respond to users’ varying needs and preferences.
Approach: They propose a test-time user-preference alignment strategy that optimizes the persona prompt, ensuring real-time preference alignment through textual loss feedback between simulated and ground-truth responses.
Outcome: The proposed framework outperforms baseline methods in real-time and in real applications.

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