We demonstrate that RL finetuning an LLM using debate, a two-player adversarial game between a generator and a critic adjudicated by a weaker LLM judge, reduces reward hacking compared to a reinforcement learning from AI feedback (RLAIF) baseline. Reward hacking is a central obstacle in RLAIF: as training progresses, the policy learns to exploit systematic errors in its AI judge, degrading task performance, a problem that worsens precisely when the judge is weaker than the policy, the setting most relevant to overseeing increasingly capable AI systems. We study mathematics tasks, where final-answer correctness is verifiable, allowing us to measure reward hacking dynamics. We train a Gemini~2.5 Flash-class policy with a frozen, weaker Gemini~2.5 Flash Lite judge, comparing a single-player RLAIF baseline against debate. While the baseline quickly hacks the judge, debate maintains judge performance throughout training, leading to a higher peak validation accuracy (45\% performance gap recovered) that persists through many RL steps. Additional experiments show that: 1) further weakening the judge leads to faster hacking, but this can be compensated by adding an additional debate round; 2) debate incentives override prompted misalignment; 3) RL using an LLM judge has a smaller train/validation reward gap than RL from verifiable rewards; 4) learning to critique to convince the judge using ground truth labels is possible but slow. Taken together, our results are a positive update on the feasibility of debate, while highlighting that balancing multi-agent training is critical: without player constraints, adversarial training risks defaulting to critic judge-hacking. We show that critique word limits (effective up to 150 words) successfully balance the game and avoid judge hacking, though this introduces a trade-off by restricting critic expressive clarity.
The integration of artificial intelligence into medical question-answering systems has advanced rapidly; however, research remains predominantly focused on English, leaving low resource languages like Persian significantly underserved. To address this gap, this paper introduces Gaokerena, a novel family of compact Persian medical language models optimized for deployment on consumer grade hardware. As a foundational step toward localized digital healthcare, we first present Gaokerena-V, developed by training a baseline model on a newly curated 90-million-token Persian medical corpus and 20,000 expert-vetted physician Q&A pairs, which improved performance on a translated medical MMLU benchmark from 46.28% to 49.31%. Second, recognizing the critical demands of clinical reasoning, we developed Gaokerena-R by integrating a Chain-of-Thought approach with two novel Reinforcement Learning with AI Feedback (RLAIF) frameworks to optimize preference-based reasoning. Despite utilizing the same baseline architecture and a smaller dataset than Gaokerena-V, Gaokerena-R achieved a superior benchmark score of 52.98%. Furthermore, both models are equipped with custom-developed uncertainty heads that predict the model's confidence in its responses based solely on internal hidden states. While these results demonstrate significant progress in Persian medical language modeling and proactive safety estimation, current performance levels remain insufficient for direct clinical application, highlighting the necessity for further research into robust knowledge acquisition and rigorous safety verification prior to real world deployment.
Shiping Yang, Shining Liang, Weihao Liu +4cs.CL cs.LG
Identifying faithfulness hallucinations in LLM-generated outputs remains challenging due to the scarcity of high-quality annotated data. Recent work relies on advanced LLMs to synthesize training data, including rationales, labels, and hallucinated claims. However, these methods treat the generator as a static component, limiting iterative improvement of the detector. To address this limitation, we introduce Hallucination Self-Play (HSP), a novel framework that enables the detector to bootstrap with an evolved generator. HSP involves two roles initialized from the same base model, a detector that assesses the faithfulness of model outputs, and a generator that produces increasingly hard-to-detect hallucinated responses. Specifically, the detector is first fine-tuned on human-labeled data and then employed as a reward model to train the generator via reinforcement learning from AI feedback (RLAIF). In turn, the evolved generator synthesizes hallucination data to further optimize the detector through rule-based reinforcement learning. Experiments on RAGTruth benchmark and two model families demonstrate that the proposed framework can progressively enhance a small LLM to match or even outperform advanced LLMs without external supervision. Our code is available at https://anonymous.4open.science/r/Hallucination-Self-Play-50B5 .
Weak-to-strong alignment offers a promising route to scalable supervision, but it can fail when a strong model becomes confidently wrong on examples that lie in the weak teacher's blind spots. Understanding such failures requires going beyond aggregate accuracy, since weak-to-strong errors depend not only on whether the strong model disagrees with its teacher, but also on how confidence and uncertainty are distributed across examples. In this work, we analyze weak-to-strong alignment through a bias-variance-covariance lens that connects misfit theory to practical post-training pipelines. We derive a misfit-based upper bound on weak-to-strong population risk and study its empirical components using continuous confidence scores. We evaluate four weak-to-strong pipelines spanning supervised fine-tuning (SFT), reinforcement learning from human feedback (RLHF), and reinforcement learning from AI feedback (RLAIF) on the PKU-SafeRLHF and HH-RLHF datasets. Using a blind-spot deception metric that isolates cases where the strong model is confidently wrong while the weak model is uncertain, we find that strong-model variance is the strongest empirical predictor of deception across our settings. Covariance provides additional but weaker information, indicating that weak-strong dependence matters, but does not by itself explain the observed failures. These results suggest that strong-model variance can serve as an early-warning signal for weak-to-strong deception, while blind-spot evaluation helps distinguish whether failures are inherited from weak supervision or arise in regions of weak-model uncertainty.