LLM agents often give inconsistent true and false probabilities for claims
Do "True" and "False" Add Up to One? Complement Consistency in LLM-Agent Opinion Simulations
Artificial IntelligenceComputation and LanguageMultiagent SystemsSocial and Information Networks
Summary
When AI agents estimate how likely a statement is true or false, their answers for a claim and its opposite should add up to one. The authors tested three smaller AI language models and found they often do not add up perfectly, sometimes adding to more than one. This inconsistency happens even after multiple rounds of opinion sharing and rewriting the statements. They show a simple fix can reduce this error but does not always improve accuracy. Their work highlights the need to test AI-generated probabilities carefully before treating them as consistent beliefs.
What this means in practice
- •For ai system developers: Check if AI agents produce complementary probability outputs in multi-agent settings to ensure logically consistent belief updates.
- •For fact-checking teams: Improve confidence in AI-generated truth assessments by screening for probability inconsistencies across claim rewordings before use in verification pipelines.
Authors
Anouar Imel, Jin Qi
Abstract
In LLM-agent opinion simulations, each agent reports the probability that a claim is true after seeing its own previous probability and the probabilities reported by its neighbors, and that number becomes its state in the next round. If the number describes the agent's position rather than the sentence it was shown, then rewriting the claim as its complement and replacing every probability p with 1 - p should return the complementary answer, so the two reports should sum to one. We test this with three small open models: Qwen3-4B, Llama-3.2-3B and Gemma-3-4B. On 2,304 agent states taken from a running network simulation, Qwen's paired reports sum to 1.18 on average, and on 48 real fact-checking claims from AVeriTeC they again exceed one. A controlled benchmark of 24 worlds, each with exactly two possible outcomes, shows the same failure in all three models. The discrepancy is two to ten times larger than the change produced by a same-meaning paraphrase, and it persists under repeated sampling and across peer group sizes and report strengths. When the reports are fed back into two populations that start from complementary states, the populations do not remain mirror images: their divergence is positive after five rounds for every model. Averaging each answer with the complement of its paired answer restores consistency by construction and lowers Brier loss averaged over the two wordings, but at the final round it beats the better of the two original wordings for only one of the three models. A schedule-by-targeting experiment on the same model gives a small, stable interaction because such sweeps keep the claim wording fixed. Consistency under rewording therefore needs its own test before simulated probabilities are read as beliefs