5 papers
FineRef: Fine-Grained Error Reflection and Correction for Long-Form Generation with Citations
Yixing Peng, Licheng Zhang, Shancheng Fang +3
Generating with citations is crucial for trustworthy Large Language Models (LLMs), yet even advanced LLMs often produce mismatched or irrelevant citations. Existing methods over-op…
ConsistCompose: Unified Multimodal Layout Control for Image Composition
Xuanke Shi, Boxuan Li, Xiaoyang Han +4
Unified multimodal models that couple visual understanding with image generation have advanced rapidly, yet most systems still focus on visual grounding-aligning language with imag…
Alignment Revisited: Are Large Language Models Consistent in Stated and Revealed Preferences?
Zhuojun Gu, Quan Wang, Shuchu Han
Recent advances in Large Language Models (LLMs) highlight the need to align their behaviors with human values. A critical, yet understudied, issue is the potential divergence betwe…
Zero-Shot Detection of LLM-Generated Text using Token Cohesiveness
Shixuan Ma, Quan Wang
The increasing capability and widespread usage of large language models (LLMs) highlight the desirability of automatic detection of LLM-generated text. Zero-shot detectors, due to…
Improved Long-Form Speech Recognition by Jointly Modeling the Primary and Non-primary Speakers
Guru Prakash Arumugam, Shuo-yiin Chang, Tara N. Sainath +3
ASR models often suffer from a long-form deletion problem where the model predicts sequential blanks instead of words when transcribing a lengthy audio (in the order of minutes or…