Papers by Wenqian Cui
VoxEval: Benchmarking the Knowledge Understanding Capabilities of End-to-End Spoken Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Existing question-answering benchmarks fail to evaluate SLMs’ knowledge understanding due to their inability to support end-to-end speech evaluation and account for varied input audio conditions. |
| Approach: | They propose a new question-answering benchmark that assesses SLMs’ knowledge understanding through pure speech interactions. |
| Outcome: | The proposed benchmark maintains speech format for both inputs and outputs, evaluates model robustness across diverse input audio conditions, and pioneers the assessment of complex tasks like mathematical reasoning in spoken format. |
Recent Advances in Speech Language Models: A Survey (2025.acl-long)
Copied to clipboard
Wenqian Cui, Dianzhi Yu, Xiaoqi Jiao, Ziqiao Meng, Guangyan Zhang, Qichao Wang, Steven Y. Guo, Irwin King
| Challenge: | Text-based Large Language Models (LLMs) are a promising solution for end-to-end speech interaction. |
| Approach: | They propose to build a framework that allows users to input text and translate it into speech . they propose to use a text-only LLM and a "textto-speech" framework to generate a response based on this transcription . |
| Outcome: | The survey offers an overview of recent approaches to building SpeechLMs . it outlines core architectural components, training methodologies, evaluation strategies and challenges . |
Learning Autonomous Driving Tasks via Human Feedbacks with Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing systems focus on making autonomous driving decisions without human interaction, but human-like decision-making is still an important factor in designing autonomous driving systems. |
| Approach: | They propose a framework leveraging Large Language Models for learning human-centered driving decisions from diverse simulation scenarios and environments that incorporate human feedback. |
| Outcome: | The proposed framework can match baseline extensively trained reinforcement learning models in driving scenarios and store optimal driving programming policy using Retrieval Augmented Generation (RAG). |
MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks focus on evaluating single-round interactions, neglecting other critical aspects. |
| Approach: | They propose a benchmark to evaluate full-duplex speech language models in multi-round settings . they segment continuous full-dual dialogues into discrete turns for evaluation . |
| Outcome: | The proposed benchmark compared full-duplex speech language models with full-dual speech models . the results show that the models perform better in multi-round settings than standard models compared to benchmarks . |
From General Reward to Targeted Reward: Improving Open-ended Long-context Generation Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Current research on long-form context in Large Language Models (LLMs) focuses on understanding of long-contexts, but the open-ended Long Text Generation (Open-LTG) remains underexplored. |
| Approach: | They propose a method that uses data synthesis and a reward signal to enhance model performance. |
| Outcome: | The proposed method outperforms GPT-4-Turbo and improves performance by 20% on the Open-LTG task. |