IsoSci: A Benchmark of Isomorphic Cross-Domain Science Problems for Evaluating Reasoning versus Knowledge Retrieval in LLMs · 相关技术
相关技术
ECTEmpirical Privacy AuditingEfficient Majority-then-StoppingEVAERPENAELSACROSACTABIABLEANNARIARTATEAdaptive Batch ScalingAdaptive Context CompressionAttention-based multiple instance learningAttribute Prefix AdapterAugmented Latent IntrinsicsAutoregressive large language modelsBenchmarkCAPCROPCTLCTUChain-of-Thought explanation paradigmchain-of-thought reasoningContinuous Integrate-and-FireDELDIFDIFFDIRDIRECTDIffusion Reconstruction ErrorDNA-encoded librariesDOMDeontic Agentic ReasoningDynamic Facial Expression RecognitionDynamic Infilling AnchorsECI