Bingxuan Hou — accepted AI-conference papers

2025

Bold Claims or Self-Doubt? Factuality Hallucination Type Detection via Belief State

Dongyu Zhang, Qingqing Hong, Bingxuan Hou, Jiayi Lin, Chenyang Zhang, Jialin Li +1

EMNLP 2025

Large language models are prone to generating hallucination that deviates from factual information. Existing studies mainly focus on detecting the presence of hallucinations but lack a systematic classification approach, which hinders deeper exploration of their characteristics. To address this, we

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Disentangle to Decay: Linear Attention with Trainable Decay Factor

Haibo Tong, Chenyang Zhang, Jiayi Lin, Bingxuan Hou, Qingqing Hong, Junli Wang

COLING 2025main

Linear attention enhances inference efficiency of Transformer and has attracted research interests as an efficient backbone of language models. Existing linear attention based models usually exploit decay factor based positional encoding (PE), where attention scores decay exponentially with increasi…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗