Truthful AI

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Evans et al. 2021 - Truthful AI: Developing and Governing AI that Does Not Lieconcept0.844
  Reference establishing the truthfulness/honesty distinction and need for honest AI
• truthfulnessconcept0.794
  A correctness condition requiring assertions to be true.
• Truthfulness Classifiermethod0.778
  Binary LLM classifier determining whether a model response to a TruthfulQA question is truthful (1) or deceptive (0)
• TruthfulQA Truthfulness Classifiermethod0.774
  Binary classifier evaluating factual accuracy of model responses on TruthfulQA benchmark
• AI Deceptionconcept0.773
  Central problem the paper addresses: AI systems producing misaligned outputs or behaviors that mislead users or other agents
• Input-truthconcept0.771
  Correctness of input statements to an LLM, as opposed to output-truth (correctness of model-generated outputs).
• TruthfulQA Benchmark Evaluationmethod0.759
  Applied as an out-of-domain test of whether deception features track general representational honesty vs. consciousness-specific gating
• Meta AIinstitute0.759
  Affiliation of Ziyu Guo and Rain Liu.