Papers by Peiyi Zhang

8 papers
AFT-Tab: Adversarial Fine-Tuning for Tabular Data Synthesis with Long Text Columns (2026.acl-long)

Copied to clipboard

Challenge: Existing tabular data synthesis methods fail to account for cross-modal heterogeneity of real-world tables, where structured continuous and discrete attributes coexist with unstructured long-text columns.
Approach: They propose a framework that synergistically trains an LLM-based text generator and a deep-learning-based non-textual generator to quantify cross-modal semantic alignment.
Outcome: The proposed framework outperforms state-of-the-art frameworks in fidelity, diversity, and task utility.
Diving into Mitigating Hallucinations from a Vision Perspective for Large Vision-Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing benchmarks focus on coarse-grained hallucination detection and fail to capture hallucinics . vision encoders exhibit unique hallucinian characteristics, but suboptimal of simple feature fusion.
Approach: They propose a visual encoder that employs different training paradigms to instill inductive biases in visual encoded models.
Outcome: The proposed system reduces hallucinations and improves model performance.
DSQG-Syn: Synthesizing High-quality Data for Text-to-SQL Parsing by Domain Specific Question Generation (2025.findings-naacl)

Copied to clipboard

Challenge: Existing methods for generating SQL queries using natural language questions produce inconsistent NLQ-SQL pairs.
Approach: They propose a text-to-SQL data synthesis framework that generates domain-relevant questions . they synthesize NLQ-SqL pairs that are domain-specific and intent-consistent .
Outcome: The proposed method outperforms closed-source LLMs on the Text-to-SQL task.
PCA-Bench: Evaluating Multimodal Large Language Models in Perception-Cognition-Action Chain (2024.findings-acl)

Copied to clipboard

Challenge: a new multimodal decision-making benchmark evaluates the integrated capabilities of multimodal large language models.
Approach: They propose a multimodal decision-making benchmark for evaluating MLLMs . they propose an automatic evaluation protocol to assess 10 prevalent ML models .
Outcome: The proposed benchmark improves performance of multimodal large language models in three scenarios . the model is required to integrate multiple capabilities to make accurate decisions .
Instantly Learning Preference Alignment via In-context DPO (2025.naacl-long)

Copied to clipboard

Challenge: Presently, mainstream approaches to HPA heavily depend on fine-tuning . however, the huge computational and annotation costs of fine-timing are hard to ignore .
Approach: They propose a tuning-free approach to HPA using LLMs' decoding . they first rethink the derivation procedures of DPO and build an instant scorer .
Outcome: The proposed approach outperforms existing methods even with tuning-free baselines and an upgraded scorer.
Be a Multitude to Itself: A Prompt Evolution Framework for Red Teaming (2024.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) have gained increasing attention for their capacity to generate harmful content.
Approach: They propose a scalable evolution framework to evolve red teaming prompts across breadth and depth dimensions, facilitating automatic generation of numerous high-quality and diverse red team prompts.
Outcome: The proposed framework surpasses existing red teaming methods on attack success rate and diversity.
Dynamic Task Vector Grouping for Efficient Multi-Task Prompt Tuning (2025.findings-acl)

Copied to clipboard

Challenge: Existing approaches transfer the soft prompt to low-source targets by combining all source tasks or a single “high-similar” source task one-time-only.
Approach: They propose a method to group similar source tasks based on two metrics: target similarity and knowledge consistency.
Outcome: The proposed method reduces negative transfer and improves performance on low-source targets.
SPFT-SQL: Enhancing Large Language Model for Text-to-SQL Parsing by Self-Play Fine-Tuning (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for self-play fine-tuning do not generate new information and the large number of correct SQL queries produced by the opponent model reduces the main model’s ability to generate accurate SQL queries.
Approach: They propose a self-play fine-tuning method tailored for the Text-to-SQL task that synthesizes high-quality fine- tuning data iteratively based on the database schema and validation feedback to enhance model performance.
Outcome: The proposed method outperforms existing state-of-the-art methods on six open-source LLMs and five widely used 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