Papers by Wenkai Zhou

8 papers
BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for embedding human personality traits into LLMs are limited by realism and validity issues.
Approach: They propose to use a large-scale dataset to embed human personality traits into LLMs . they use supervised fine-tuning and direct preference optimization to train LLM models .
Outcome: The proposed methods outperform prompting on personality assessments and IPIP-NEO, and show higher conscientiousness, agreeableness, lower extraversion, and lower neuroticism on reasoning tasks.
Correct When Paired, Wrong When Split: Decoupling and Editing Modality-Specific Neurons in MLLMs (2026.acl-long)

Copied to clipboard

Challenge: Existing knowledge editing paradigms suffer from editing decoupling failures . entity knowledge is sequestered into disentangled modality-specific pathways .
Approach: They propose a method that explicitly disentangles and localizes modality-specific neuron groups for targeted knowledge.
Outcome: The proposed method outperforms baselines in reliability and consistency while preserving model locality.
Bridging Semantic and Modality Gaps in Zero-Shot Captioning via Retrieval from Synthetic Data (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for zero-shot image captioning fail to bridge the semantic gap between images and textual inputs.
Approach: They propose a retrieval-based framework that leverages only existing synthetic image-text pairs as its search corpus to bridge the gap when using synthetic data for captioning.
Outcome: The proposed method bridges the semantic gap between a synthetic image and its input text . it extracts image-related textual descriptions to mitigate the modality gap during decoding .
Distilling Rule-based Knowledge into Large Language Models (2025.coling-main)

Copied to clipboard

Challenge: Recent advances in large language models have broadened their applicability across diverse realworld scenarios.
Approach: They propose to encode rule-based knowledge into large language models by using strong in-context abilities to extract the knowledge from the textual rules and then explicitly encode it into the parameters of LLMs.
Outcome: The proposed learning paradigm is much more efficient than example-based learning in both sample size and generalization ability.
RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models (2021.emnlp-main)

Copied to clipboard

Challenge: Backdoor attacks are a serious threat to the safety of reusing deep neural networks (DNNs).
Approach: They propose an efficient online defense mechanism based on robustness-aware perturbations to distinguish poisoned and clean samples to defend against backdoor attacks on natural language processing models.
Outcome: The proposed method achieves better defending performance and lower computational costs than existing defense methods.
Rethinking Stealthiness of Backdoor Attack against NLP Models (2021.acl-long)

Copied to clipboard

Challenge: Existing backdoor attacks are not stealthy to system deployers or users.
Approach: They propose a novel backdoor attack method based on negative data augmentation and modifying word embeddings that is much stealthier while maintaining pretty good attacking performance.
Outcome: The proposed method is much stealthier while maintaining pretty good attacking performance.
AlphaContext: An Evolutionary Tree-based Psychometric Context Generator for Creativity Assessment (2026.acl-long)

Copied to clipboard

Challenge: Existing LLM-based tools struggle with insufficient assessment cues, weak narrative coherence, limited stylistic diversity, and poor support for creative thinking.
Approach: They propose an evolutionary tree-based psychometric context generator that integrates rule-guided outline planning, sentence-level MCTS generation, MAP-Elites quality-diversity optimization and assessment-guide refiner simulation.
Outcome: The proposed tool outperforms strong LLMs and structured frameworks on 7 evaluation dimensions and shows higher alignment with expert-designed contexts.
PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for generating presentations from documents focus on improving and evaluating content quality in isolation, overlooking visual appeal and structural coherence.
Approach: They propose an edit-based presentation generation system that analyzes and iterates on slides to create new slides.
Outcome: The proposed presentation generation tool outperforms existing methods in three dimensions . it analyzes slides, iterates and generates edit actions based on selected slides .

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