Aligning large language models (LLMs) with human preferences has proven to drastically
improve usability and has driven rapid adoption as demonstrated by ChatGPT. Alignment …

Large Language Models (LLMs) trained on extensive textual corpora have emerged as
leading solutions for a broad array of Natural Language Processing (NLP) tasks. Despite …

Aligning large language models (LLMs) to human values has become increasingly
important as it enables sophisticated steering of LLMs. However, it requires significant …

Alignment with human preference is a desired property of large language models (LLMs).
Currently, the main alignment approach is based on reinforcement learning from human …

Alignment has become a critical step for instruction-tuned Large Language Models (LLMs)
to become helpful assistants. However, effective evaluation of alignment for emerging …

Large language models (LLMs) have shown impressive success in various applications.
However, these models are often not well aligned with human intents, which calls for …

Aligning large language models (LLMs) with human values and intents critically involves the
use of human or AI feedback. While dense feedback annotations are expensive to acquire …

Alignment tuning has become the de facto standard practice for enabling base large
language models (LLMs) to serve as open-domain AI assistants. The alignment tuning …

Finetuning language models with reinforcement learning (RL), eg from human feedback
(HF), is a prominent method for alignment. But optimizing against a reward model can …

Big models, exemplified by Large Language Models (LLMs), are models typically pre-
trained on massive data and comprised of enormous parameters, which not only obtain …