arXiv:2509. 26169v2 Announce Type: replace Abstract: Alignment of large language models remains a central challenge in natural language processing.
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: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: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:2608.21023v1 Announce Type: new Abstract: Word alignment has traditionally been studied between sentences, but many cross-lingual tasks increasingly require correspondences across full document...
arXiv:2609.05899v1 Announce Type: cross Abstract: Aligning large language models with human preferences remains a challenge, primarily due to the critical role of preference data quality in effective...
arXiv:2606. 09635v1 Announce Type: cross Abstract: Ensuring the reliability of Large Language Models (LLMs) under distribution drift requires inference-time adaptation.
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 proposes a method for culturally aligning large language models (LLMs) using soft prompt tuning optimized via Differential Evolution (DE). Unlike traditional fine‑tuning or reinforcement learning, this approach keeps model weights frozen and requires no preference data, instead leveraging aggregated survey scores from Hofstede's Value Survey Module (VSM13). Experiments on four countries and four instruction‑tuned models show that DE‑optimized prompts reduce cultural discrepancy, improve agreement with the World Values Survey, and are preferred in blinded pairwise evaluations by LLM judges.
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.
The paper investigates how preference tuning—optimizing language models with explicit preference signals—behaves when applied to new domains. It systematically compares five alignment objectives and several adaptation strategies, such as target‑domain supervised fine‑tuning and pseudo‑labeling, across summarization, question‑answering helpfulness, and safety tasks. Results show that while pseudo‑labeling reduces domain‑shift degradation, it also causes mode collapse, highlighting a trade‑off between generalization and diversity.
Ready2Blend is a method that blends natural-language instructions with learned alignment prompts to enable continual alignment of large language models without retraining the backbone. It uses AlignFormer to map each requirement to a fixed-length prompt stored in a modular bank, while keeping the backbone and prior prompts frozen. The approach achieves 93.1–98.5% of joint‑training performance, retains prior knowledge, and reduces training time by up to 4.3×, also allowing weighted personalization and order‑free composition.
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.