Multi-LLM Adaptive Conformal Inference for Reliable LLM Response

ICLR 2026 Conference Submission14675 Authors

Keywords: LLM Response Factuality, Conformal Inference, Multi-LLM

TL;DR: Develop a new conformal inference method to guarantee the factuality of LLM responses and maximize its practicality by using multi-LLMs.

Abstract: Ensuring factuality is essential for the safe use of Large Language Models (LLMs) in high-stakes domains such as medicine and law. Conformal inference provides distribution-free guarantees, but existing approaches are either overly conservative, discarding many true-claims, or rely on adaptive error rates and simple linear models that fail to capture complex group structures. To address these challenges, we reformulate conformal inference in a multiplicative filtering setting, modeling factuality as a product of claim-level scores. Our method, Multi-LLM Adaptive Conformal Inference MACI, leverages ensembles to produce more accurate factuality scores, which in our experiments led to higher retention, while validity is preserved through group-conditional calibration. Experiments show that MACI consistently achieves user-specified coverage with substantially higher retention and lower time cost than baselines. Our anonymized repository is available at https://github.com/Anonymous2026conf/MACI.git.

Primary Area: probabilistic methods (Bayesian methods, variational inference, sampling, UQ, etc.)

Submission Number: 14675