analiza aiqbench
This research addresses a critical limitation in large language models by introducing a framework that assesses future predictability before committing to specific answers, thereby significantly reducing hallucinations in volatile scenarios. By regulating answer commitment based on temporal dynamics rather than unconditional forecasting, the proposed method offers a more robust approach to reliable temporal reasoning under uncertainty. The findings highlight the importance of explicit predictability assessment for enhancing the safety and accuracy of AI systems when dealing with future-oriented queries.
Is the Future Predictable? Modeling Future Predictability for Reliable Temporal Reasoning
arXiv:2610.14073v1 Announce Type: cross Abstract: Large language models (LLMs) remain unreliable when reasoning about the future. Existing models often overlook the difference among future states, committing to specific answers even when the queried facts are inherently volatile. To capture this challenge, we introduce ChronoRegime, a future-oriented temporal reasoning task that requires models to determine whether historical temporal evidence justifies commitment to a future answer. Furthermore, we propose Confidence-Aware Temporal Reasoning (CTR), a framework that estimates future predictability from temporal dynamics and regulates answer commitment accordingly. Rather than performing unconditional forecasting, CTR commits only when the reconstructed evidence supports the target future state. Across multiple LLMs, CTR improves strict overall accuracy by 6.7 percentage points and reduces hallucination rates by 18.4 percentage points on average over the plain QA baseline. These results demonstrate that explicit predictability assessment is an effective mechanism for safer and more reliable temporal reasoning under future uncertainty.
Title:Is the Future Predictable? Modeling Future Predictability for Reliable Temporal Reasoning
Abstract:Large language models (LLMs) remain unreliable when reasoning about the future. Existing models often overlook the difference among future states, committing to specific answers even when the queried facts are inherently volatile. To capture this challenge, we introduce ChronoRegime, a future-oriented temporal reasoning task that requires models to determine whether historical temporal evidence justifies commitment to a future answer. Furthermore, we propose Confidence-Aware Temporal Reasoning (CTR), a framework that estimates future predictability from temporal dynamics and regulates answer commitment accordingly. Rather than performing unconditional forecasting, CTR commits only when the reconstructed evidence supports the target future state. Across multiple LLMs, CTR improves strict overall accuracy by 6.7 percentage points and reduces hallucination rates by 18.4 percentage points on average over the plain QA baseline. These results demonstrate that explicit predictability assessment is an effective mechanism for safer and more reliable temporal reasoning under future uncertainty.
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
arXiv:2610.14073 [cs.CL]
(or arXiv:2610.14073v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2610.14073 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 254 cuvinte
Subiecte conexe
Links #5: 2026/07
LessWrong · 31 iul. 2026
Game Design Creativity evals
LessWrong · 12 oct. 2026
Runway’s WorldPrompt and the Engineering of Real-Time Worlds
Latent Space · 25 sept. 2026
Scientific reasoning does not reliably translate into scientific forecasting in frontier AI
arXiv · 21 iul. 2026