Aligning large language models to human preferences is crucial for real-world deployment but frequently incurs an alignment tax, leading to the catastrophic forgetting of pre-trained general capabilit...
The paper introduces BALIGN, a balanced data selection strategy designed to reduce catastrophic forgetting—referred to as the alignment tax—in large language models during preference-based alignment. By analyzing preference optimization gradients, the authors identify three data-centric features that influence parameter drift: the reference model's log-probability margin, token length differences between chosen and rejected responses, and TF‑IDF similarity to general capability corpora. BALIGN aggregates these features into a composite risk score to filter out high-risk preference samples, thereby preserving foundational capabilities while maintaining alignment gains with minimal computational overhead.
arXiv:2607. 03248v1 Announce Type: cross Abstract: The alignment of large language models with human preferences is commonly achieved through Reinforcement Learning from Human Feedback or Direct Preference Optimization.
arXiv:2504. 06659v2 Announce Type: replace-cross Abstract: Despite advances in Preference Alignment (PA) for Large Language Models (LLMs), mainstream methods like reinforcement learning with human feedback face notable challenges.
arXiv:2509. 26169v2 Announce Type: replace Abstract: Alignment of large language models remains a central challenge in natural language processing.
arXiv:2504. 07856v4 Announce Type: replace Abstract: Curriculum learning enhances Direct Preference Optimization (DPO) for aligning Large Language Models (LLMs), yet existing methods rely on a one-dimensional view of difficulty.
arXiv:2509. 23982v2 Announce Type: replace-cross Abstract: Preference alignment is a critical step in making Large Language Models (LLMs) useful and aligned with (human) preferences.
arXiv:2609.06893v1 Announce Type: cross Abstract: Direct preference optimization DPO is a promising offline approach for aligning large language models (LLMs) due to its simplicity, computational eff...
arXiv:2508.04698v2 Announce Type: replace Abstract: LLM-powered conversational assistants are often deployed in a one-size-fits-all manner, which fails to accommodate individual user preferences. Rec...
arXiv:2606. 09850v1 Announce Type: new Abstract: Post-training alignment algorithms are predominantly evaluated as black boxes, obscuring how they reshape language models' internal computations.
arXiv:2410. 15595v4 Announce Type: replace Abstract: With the rapid advancement of large language models (LLMs), aligning policy models with human preferences has become increasingly critical.
The paper introduces DSPA, a dynamic sparse autoencoder (SAE) steering technique that aligns language model outputs with user preferences during inference, avoiding costly weight updates. DSPA constructs a conditional-difference map from preference triples to adjust token-active latents, improving MT‑Bench scores and matching AlpacaEval performance on models like Gemma‑2 and Qwen3 while preserving accuracy. It demonstrates robustness with limited preference data, outperforms the two‑stage RAHF‑SCIT pipeline in FLOPs, and reveals that preference directions are largely driven by discourse and stylistic cues.