2 papers
cs.CL2026
The First Token Knows: Single-Decode Confidence for Hallucination Detection
Mina Gabriel
Self-consistency detects hallucinations by generating multiple sampled answers to a question and measuring agreement, but this requires repeated decoding and can be sensitive to le…
cs.AI2026
From Natural Language to Executable Narsese: A Neuro-Symbolic Benchmark and Pipeline for Reasoning with NARS
Mina Gabriel, Pei Wang
Large language models (LLMs) are highly capable at language generation, but they remain unreliable when reasoning requires explicit symbolic structure, multi-step inference, and in…