Large Language Models (LLMs) are aligned to human preferences, after pre-training and supervised fine-tuning steps. However, standard RL alignment steps such as RLHF do not focus on factuality of LLMs, hence they may generate non-factual information, which could result in unintended consequences. In response, a number of factuality alignment approaches have been proposed in the literature which claim to improve factuality of LLMs on their own benchmarks. However, these methods have not been reproduced independently and are also not comparable since each uses a different base model, training data, evaluation set, judge, and metric. In this paper, we present the first independent reproduction of five factuality alignment methods, which span on-policy RL (PPO, GRPO, and Dr.~GRPO) and offline preference optimization (DPO and KTO), and compare them on a common benchmark with common evaluation metrics. We found that none of these methods reproduces in full, and on the common benchmark none of the methods significantly outperforms the base model. On closer inspection, the rewards optimize for format, length, or brevity rather than factuality and relevance, whereas the choice between on-policy and offline training matters little. Furthermore, the evaluation metrics and benchmarks are also part of the problem since they do not measure relevance of text to the prompt. Since there is no ground truth associated with the prompts, the reliance on LLM judges and retrieval for verification also makes the evaluation fragile. We release our code, data, and checkpoints.

翻译：暂无翻译