QA datasets
PulseAugur coverage of QA datasets — every cluster mentioning QA datasets across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New RL Framework CalibraRL Tackles LLM Hallucinations in RAG
Researchers have developed CalibraRL, a novel reinforcement learning framework designed to reduce hallucinations in large language models (LLMs) used in retrieval-augmented generation (RAG). This new approach incorporat…
-
New method disentangles LLM knowledge interaction in multi-step analysis
Researchers have developed a novel method to analyze how large language models (LLMs) interact with different types of knowledge, specifically external context knowledge (CK) and internal parametric knowledge (PK). This…
-
New framework audits and mitigates privacy leakage in cloud-edge LLM collaboration
Researchers have developed a new framework to audit and mitigate privacy leakage in cloud-edge collaborative decoding systems. These systems use a small language model on edge devices to process private data and fuse it…