From the 1 of 7 linked papers with an AI index.
7 papers
Discrete Diffusion Models: A Unified Framework from Tokenization to Generation
Ye Yuan, Weien Li, Rui Song +20
The paper proposes a unified framework for discrete denoising diffusion models that ties together tokenization, vocabulary design, and generation methods, showing how existing appr…
NTS-CoT: Mitigating Hallucinations in LLM-based News Timeline Summarization with Chain-of-Thought Reasoning
Feng Lyu, Huiqin Yan, Sijing Duan +5
The rapid updates of online news make tracking event developments challenging, highlighting the need for timeline summarization (TLS). Hallucinations, where LLM-generated content d…
Learning Discriminative and Generalizable Anomaly Detector for Dynamic Graph with Limited Supervision
Yuxing Tian, Yiyan Qi, Fengran Mo +3
Dynamic graph anomaly detection is critical for many real-world applications but remains challenging due to the scarcity of labeled anomalies. Existing methods are either unsupervi…
Learning to Route Queries to Heads for Attention-based Re-ranking with Large Language Models
Yuxing Tian, Fengran Mo, Zhiqi Huang +2
Large Language Models (LLMs) have recently been explored as fine-grained zero-shot re-rankers by leveraging attention signals to estimate document relevance. However, existing meth…
Preference Heads in Large Language Models: A Mechanistic Framework for Interpretable Personalization
Weixu Zhang, Ye Yuan, Changjiang Han +7
Large Language Models (LLMs) exhibit strong implicit personalization ability, yet most existing approaches treat this behavior as a black box, relying on prompt engineering or fine…
Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired Decoding
Weixu Zhang, Fanghua Ye, Qiang Gao +7
Large language models (LLMs) often produce content that contradicts or overlooks information provided in the input context, a phenomenon known as faithfulness hallucination. In thi…