Entity · technique

CARE-PPO

techniqueactiveprovisionalcare-ppo-6a5d79f4·1 events·first seen 6d ago

Aliases: CARE-PPO

Co-occurring entities

Proximal Policy Optimization Qwen3

More like this (12)

PPO UST CarePath PACT MedCPT DPPO CaresAI SPPO ProAct PAC-ACT HPRO Personal Health Agent CISPO

Recent events (1)

5arXiv · cs.CL·6d ago·source ↗

CARE-PPO: PPO-based RL framework for joint quantitative prediction and confidence estimation in LLMs

Researchers introduce CARE-PPO, a reinforcement learning fine-tuning framework that jointly trains LLMs for numerical prediction accuracy and calibrated confidence estimation. The approach repurposes the PPO critic as a confidence estimator at inference time, using a Confidence-Aligned Reward for Estimation derived from prediction error. Evaluated on healthcare and finance tasks with Qwen-3 4B and 8B models, CARE-PPO outperforms logit-based and verbalized confidence baselines and shows improved out-of-distribution generalization. The work addresses the hallucination and overconfidence problems that limit LLM deployment in high-stakes quantitative domains.

Evaluation and Benchmarking Alignment and RLHF Proximal Policy Optimization Qwen3 CARE-PPO