barbecue
PulseAugur coverage of barbecue — every cluster mentioning barbecue across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
BenchMIRT tool questions LLM safety evaluations, finds reasoning bias
A new tool called BenchMIRT has been developed to evaluate the effectiveness of LLM safety and capability assessments. Initial testing on the barbecue (BBQ) social bias evaluation revealed that the questions primarily d…
-
New LLM benchmark reveals "misfired alignment" overriding evidence
A new research paper, "The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs," introduces the concept of "misfired alignment," where language models reject warranted conclusions due to overzealo…
-
New MARI Method Enhances LLM Alignment Without Weight Modification
Researchers have developed a new method called Multi-Adapter Representation Interventions via Energy Calibration (MARI) to better align large language models with desired behaviors without altering their core weights. M…