arXiv:2509. 23102v4 Announce Type: replace Abstract: Reinforcement learning from human feedback (RLHF) has emerged as the standard paradigm for aligning large language models with human preferences.
Robust Nash Alignment introduces a game-theoretic framework that seeks a policy with a high worst-case win rate against both an adversarial competitor and any preference kernel within an ambiguity set around a nominal preference. The authors propose a four-player primal-dual proxy game and an optimistic mirror descent-ascent algorithm to efficiently optimize this robust objective, proving convergence guarantees and demonstrating improved performance in controlled tabular games and LLM alignment experiments.
arXiv:2503.00030v3 Announce Type: replace-cross Abstract: Self-play-based policy optimization has emerged as an effective approach for fine-tuning large language models (LLMs), formulating preference...
arXiv:2606. 01561v1 Announce Type: new Abstract: Aligning Large Language Models (LLMs) with human preferences is often formulated via Direct Preference Optimization (DPO).
arXiv:2608. 15402v1 Announce Type: new Abstract: Generative model alignment has received broad interest, and significant progress has been made in supervised fine-tuning and inference-time computation.
Swiss-Knife is a framework that extends decode‑time alignment for frozen language models by treating the alignment specification as a runtime object. It introduces hot‑swappable scoring blades, a batch normaliser, a pairwise aggregation operator, and a selection rule, and characterises admissible aggregation operators with a representation theorem. In experiments, Swiss‑Knife paired with DPO‑LoRA blades and an uncertainty‑aware pairwise tournament outperforms six existing decode‑time methods, achieving a higher harmonic F1 score, lower refusal rate, and faster objective reconfiguration.
arXiv:2609.08082v1 Announce Type: new Abstract: Preference-based fine-tuning methods such as RLHF and DPO require substantial compute and large preference datasets. They also need direct access to th...
The paper presents a new scaling law for reward optimization in AI alignment, showing that performance scales as Θ(√min{log(M), K}), where M is the number of preference comparisons used to train a proxy reward model and K is the KL‑divergence budget relative to a reference policy. The authors derive this law using an information‑theoretic model, prove its tightness, and validate it with extensive experiments involving a 70B gold reward model and smaller proxy models (0.6B–4B). The empirical results demonstrate a strong fit (R² 97–99 %) across different model sizes, noise levels, and optimization methods, suggesting that reward optimization behaves like a simple selection task over IID Gaussian variables with noisy feedback.
arXiv:2607. 02781v1 Announce Type: cross Abstract: Inference-time alignment steers a frozen language model during decoding using auxiliary reward signals, avoiding the cost of repeated weight updates.
arXiv:2512. 15765v3 Announce Type: replace Abstract: Data valuation is a natural framework for understanding which preference datasets matter most when aligning a Large Language Model (LLM) using multiple sources.
arXiv:2607. 26094v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) is the standard approach for aligning large language models with human preferences, but its quality is limited by static, task-agnostic reward models.
The paper revisits the distortion problem in Reinforcement Learning from Human Feedback (RLHF) for aligning large language models. It shows that exponential degradation in user utility, previously attributed to RLHF, actually stems from a mismatch between the preference data distribution and the KL reference policy. By deriving tight bounds across different KL regularization regimes, the authors demonstrate that when the two distributions match, RLHF achieves near‑optimal distortion, and they recommend using on‑policy data or pre‑fine‑tuning on data close to the true preference distribution.