Aligning language models to follow instructions

Efficient training of language models to fill in the middle

Phonetic forced alignment for low-resource language varieties: Model training and evaluation on Chengdu Mandarin

Phonetic forced alignment is a key technique in phonetic research, yet existing alignment systems lack specialized models for low-resource language varieties. We address this by training text-dependent and text-independent aligners for Chengdu Mandarin using a 17-hour corpus and a custom G2P dictionary.

Phonetic forced alignment for low-resource language varieties: Model training and evaluation on Chengdu Mandarin

arXiv:2607. 21332v1 Announce Type: cross Abstract: Phonetic forced alignment is a key technique in phonetic research, yet existing alignment systems lack specialized models for low-resource language varieties.

Evaluating large language models trained on code

Best practices for deploying language models

Cohere, OpenAI, and AI21 Labs have developed a preliminary set of best practices applicable to any organization developing or deploying large language models.

Deliberative alignment: reasoning enables safer language models

Deliberative alignment: reasoning enables safer language models Introducing our new alignment strategy for o1 models, which are directly taught safety specifications and how to reason over them.

Alignment-Aware Decoding

arXiv:2509. 26169v2 Announce Type: replace Abstract: Alignment of large language models remains a central challenge in natural language processing.

SpecAlign: Efficient Specification-Grounded Alignment of Large Language Models via Synthetic Data

arXiv:2606. 16276v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly deployed in real-world applications, alignment is no longer governed by a single universal notion of safety or helpfulness, but instead by provider- or application-specific model specifications.

PolicyAlign: Direct Policy-Based Safety Alignment for Large Language Models

Safety alignment of large language models (LLMs) typically depends on high-quality supervision data, such as safe demonstrations or preference pairs. However, in real-world deployment, emerging safety requirements are often specified as natural-language policies, while corresponding supervision data may be costly, delayed, or unavailable.

Toward understanding and preventing misalignment generalization

We study how training on incorrect responses can cause broader misalignment in language models and identify an internal feature driving this behavior—one that can be reversed with minimal fine-tuning.

Unbiased Alignment for Large Language Models with Noisy Preferences

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.

Scaling laws for neural language models