REVIEW 6 cited by
Truthful AI: Developing and governing AI that does not lie
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
In many contexts, lying -- the use of verbal falsehoods to deceive -- is harmful. While lying has traditionally been a human affair, AI systems that make sophisticated verbal statements are becoming increasingly prevalent. This raises the question of how we should limit the harm caused by AI "lies" (i.e. falsehoods that are actively selected for). Human truthfulness is governed by social norms and by laws (against defamation, perjury, and fraud). Differences between AI and humans present an opportunity to have more precise standards of truthfulness for AI, and to have these standards rise over time. This could provide significant benefits to public epistemics and the economy, and mitigate risks of worst-case AI futures. Establishing norms or laws of AI truthfulness will require significant work to: (1) identify clear truthfulness standards; (2) create institutions that can judge adherence to those standards; and (3) develop AI systems that are robustly truthful. Our initial proposals for these areas include: (1) a standard of avoiding "negligent falsehoods" (a generalisation of lies that is easier to assess); (2) institutions to evaluate AI systems before and after real-world deployment; and (3) explicitly training AI systems to be truthful via curated datasets and human interaction. A concerning possibility is that evaluation mechanisms for eventual truthfulness standards could be captured by political interests, leading to harmful censorship and propaganda. Avoiding this might take careful attention. And since the scale of AI speech acts might grow dramatically over the coming decades, early truthfulness standards might be particularly important because of the precedents they set.
Forward citations
Cited by 6 Pith papers
-
Discovering Latent Knowledge in Language Models Without Supervision
An unsupervised technique extracts latent yes-no knowledge from language model activations by locating a direction that satisfies logical consistency properties, outperforming zero-shot accuracy by 4% on average acros...
-
Teaching Models to Express Their Uncertainty in Words
GPT-3 can learn to express well-calibrated uncertainty about its answers using natural language phrases rather than logits.
-
DECK: A Consistency x Confidence Taxonomy of LLM Hallucinations
The DECK taxonomy partitions LLM hallucinations into four detectability regimes using consistency and confidence axes, mapping each to scorer families and identifying a universal blind spot for output-level uncertaint...
-
Deceive, Detect, and Disclose: Large Language Models Play Mini-Mafia
Mini-Mafia supplies an analytical model logit(p) = v*(m-d) for mafia win probability in LLM role interactions and uses Bayesian inference to estimate per-model parameters that predict tournament results with 76.6% Bri...
-
Language Models (Mostly) Know What They Know
Language models show good calibration when asked to estimate the probability that their own answers are correct, with performance improving as models get larger.
-
A Mathematical Theory of Discursive Networks
A two-state Markov model of error propagation suggests that small amounts of cross-agent peer review can flip a network of fallible language models from a falsehood-dominant to a truth-dominant state.
Discussion (0). Sign in to comment.