4 papers
Listen, Pause, and Reason: Toward Perception-Grounded Hybrid Reasoning for Audio Understanding
Jieyi Wang, Yazhe Niu, Dexuan Xu +1
Recent Large Audio Language Models have demonstrated impressive capabilities in audio understanding. However, they often suffer from perceptual errors, while reliable audio reasoni…
LLM-Guided Semantic Bootstrapping for Interpretable Text Classification with Tsetlin Machines
Jiechao Gao, Rohan Kumar Yadav, Yuangang Li +4
Pretrained language models (PLMs) like BERT provide strong semantic representations but are costly and opaque, while symbolic models such as the Tsetlin Machine (TM) offer transpar…
Towards Reliable Long-Context Reasoning: Detecting Unanswerable Questions via FactGuard
Qian-Wen Zhang, Biao Liu, Fang Li +5
Despite the success of Large Language Models (LLMs) in long-context tasks, their reliability in recognizing unanswerable questions remains a critical challenge. In information-seek…
Sequential-NIAH: A Needle-In-A-Haystack Benchmark for Extracting Sequential Needles from Long Contexts
Yifei Yu, Qian-Wen Zhang, Lingfeng Qiao +7
Evaluating the ability of large language models (LLMs) to process lengthy contexts is critical, especially for retrieving query-relevant information embedded within them. We introd…