arXiv:2607. 15623v1 Announce Type: cross Abstract: Predictive models deployed at scale influence future data, a phenomenon called performativity.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.
arXiv:2606. 11206v1 Announce Type: cross Abstract: Supervised Fine-Tuning (SFT) is the predominant paradigm for aligning large language models (LLMs), yet it suffers from optimization instability and limited generalization.
arXiv:2606. 05165v1 Announce Type: new Abstract: Training Data Attribution (TDA) seeks to trace a model's predictions back to its training data.
arXiv:2510. 16657v3 Announce Type: replace-cross Abstract: Synthetic data has been increasingly used to train frontier generative models.
arXiv:2606. 07890v1 Announce Type: new Abstract: Performative prediction studies feedback loops that arise when predictive models are deployed in consequential domains.
arXiv:2605. 25582v2 Announce Type: replace Abstract: Reinforcement learning for large language models faces a fundamental trade-off between sample efficiency and asymptotic performance: strictly on-policy methods discard trajectories after a single update, while off-policy reuse introduces distribution mismatch that existing trust-region techniques mitigate primarily by enforcing conservative optimization, often leaving rich training signals underutilized.
arXiv:2608. 01130v1 Announce Type: new Abstract: A broad range of models face the mismatch where they are updated through trajectory losses but are evaluated by downstream task reward.