6 papers
Emo-LiPO: Listwise Preference Optimization for Fine-Grained Emotion Intensity Control in LLM-based Text-to-Speech
Yihang Lin, Li Zhou, Congwei Cao +4
Large language model (LLM)-based text-to-speech (TTS) systems enable prompt-conditioned emotional control but struggle with fine-grained emotion intensity due to the semantic -- ac…
RAGCap-Bench: Benchmarking Capabilities of LLMs in Agentic Retrieval Augmented Generation Systems
Jingru Lin, Chen Zhang, Stephen Y. Liu +1
Retrieval-Augmented Generation (RAG) mitigates key limitations of Large Language Models (LLMs)-such as factual errors, outdated knowledge, and hallucinations-by dynamically retriev…
AudioRAG: A Challenging Benchmark for Audio Reasoning and Information Retrieval
Jingru Lin, Chen Zhang, Tianrui Wang +1
Due to recent advancements in Large Audio-Language Models (LALMs) that demonstrate remarkable performance across a range of sound-, speech- and music-related tasks, there is a grow…
Aligning Language Models Using Follow-up Likelihood as Reward Signal
Chen Zhang, Dading Chong, Feng Jiang +4
In natural human-to-human conversations, participants often receive feedback signals from one another based on their follow-up reactions. These reactions can include verbal respons…
Unveiling the Achilles' Heel of NLG Evaluators: A Unified Adversarial Framework Driven by Large Language Models
Yiming Chen, Chen Zhang, Danqing Luo +3
The automatic evaluation of natural language generation (NLG) systems presents a long-lasting challenge. Recent studies have highlighted various neural metrics that align well with…
TS-Align: A Teacher-Student Collaborative Framework for Scalable Iterative Finetuning of Large Language Models
Chen Zhang, Chengguang Tang, Dading Chong +4
Mainstream approaches to aligning large language models (LLMs) heavily rely on human preference data, particularly when models require periodic updates. The standard process for it…