Papers by Ziniu Zhang

7 papers
Advancing Zero-shot Text-to-Speech Intelligibility across Diverse Domains via Preference Alignment (2025.acl-long)

Copied to clipboard

Challenge: Existing zero-shot text-to-speech systems struggle in challenging scenarios such as tongue twisters, repeated words, code-switching, and cross-lingual synthesis.
Approach: They propose a dataset that leverages preference alignment techniques to improve performance . they also extend the Direct Preference Optimization framework to accommodate diverse TTS architectures .
Outcome: The proposed dataset improves intelligibility, similarity, and audio quality for multiple models across domains.
Scalable Fine-tuning from Multiple Data Sources: A First-Order Approximation Approach (2024.findings-emnlp)

Copied to clipboard

Challenge: a new algorithm to estimate fine-tuning performance for a target task is proposed . conventional subset selection methods require repeated training on subsets of auxiliary tasks .
Approach: They propose an algorithm to fine-tune a language model for a target task by optimally using auxiliary tasks' information.
Outcome: The proposed method can estimate fine-tuning performance on CPUs in seconds.
Efficient Ensemble for Fine-tuning Language Models on Multiple Datasets (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for fine-tuning language models are efficient when adapting to a single dataset.
Approach: They propose to use an ensemble method for fine-tuning a language model to multiple datasets instead of a single adapter per task.
Outcome: The proposed method improves performance on multiple datasets while preserving low-rank adaptation properties.
Linear-Time Demonstration Selection for In-Context Learning via Gradient Estimation (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods to select demonstration examples for in-context learning are based on token embeddings.
Approach: They propose an algorithm to select demonstration examples for in-context learning of a query set . they use gradients of the output taken in the input embedding space to estimate model outputs .
Outcome: The proposed algorithm outperforms existing methods based on token embeddings by 11% . it scales up subset selection that would otherwise run full inference by 37.7 on models with 34 billion parameters .
MMInA: Benchmarking Multihop Multimodal Internet Agents (2025.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks fail to assess embodied agents in a realistic, evolving environment for compositional Internet tasks.
Approach: They propose a multihop and multimodal benchmark to evaluate embodied agents for compositional Internet tasks.
Outcome: The proposed protocol significantly improves the performance of both the single-hop and multihop web browsing abilities.
DataSciBench: An LLM Agent Benchmark for Data Science (2026.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks focus on single task, simple evaluation metrics, and readily available ground truth (GT) DataSciBench is built on curated, natural, and challenging prompts with complex evaluation criteria and uncertain GT.
Approach: They propose a benchmark for evaluating Large Language Models in data science that integrates LLM-based self-consistency and human verification to ensure accuracy.
Outcome: The proposed framework outperforms open-source models in all metrics and offers rigorous insights into LLM strengths and weaknesses.
Automated Molecular Concept Generation and Labeling with Large Language Models (2025.coling-main)

Copied to clipboard

Challenge: Concept-based models lack explainability and need predefined concepts and manual labeling in molecular science.
Approach: They propose a framework that leverages Large Language Models to generate and label predictive molecular concepts without human input.
Outcome: The proposed framework outperforms existing models on several benchmarks while maintaining explainability and allowing easy intervention.

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