Laura Ruis, Akbir Khan, Stella Biderman, Sara Hooker, Tim Rocktäschel, and Edward Grefenstette. "Large language models are not zero-shot communicators." arXiv preprint arXiv:2210.14986, 2022.

Reinforcement learning from human feedback (RLHF) utilizes human feedback to better align large language models with human preferences via online optimization against a learned reward model. Current RLHF paradigms rely on Proximal Policy Optimization (PPO), which quickly becomes a challenge to implement and scale up to large architectures. To address this difficulty we present the trlX library as a feature-complete open-source framework for RLHF fine-tuning of models up to and exceeding 70 billion parameters. We implement support for multiple types of distributed training including distributed data parallel, model sharded, as well as tensor, sequential, and pipeline parallelism.

To increase the accessibility of RLHF to researchers, we implement compute- and memory-saving features that give trlX the flexibility to support users with a wide range of compute resources. This includes offline RL methods like Implicit Language Q Learning (ILQL), low-rank adapters, and the Hydra architecture. We find offline fine-tuning offers competitive performance relative to online algorithms while being easier to implement, train, and scale. To evaluate our framework we train RLHF models on two separate well-known tasks using publicly available human preference data. Models trained with trlX achieve preference win-rates over baselines at rates comparable to the original works.

I was able to use the weird centroid-proximate tokens that Jessica Mary and Matthew Watkins discovered to associate several of the Instruct models on the OpenAI API with the base models they were initialized from. Prompting GPT-3 models with these tokens causes aberrant and correlated behaviors, and I found that the correlation is preserved between base models and Instruct versions, thereby exposing a "fingerprint" inherited from pretraining.

I was inspired to try this by JDP's proposal to fingerprint generalization strategies using correlations in model outputs on out-of-distribution inputs. This post describes his idea and the outcome of my experiment, which I think is positive evidence that this "black box cryptanalysis"-inspired approach to fingerprinting models is promising.

Leo Gao. “An Empirical Exploration in Quality Filtering of Text Data.” arXiv preprint arXiv:2109.00698, 2021.

Connor Leahy and Stella Biderman. "The Hard Problem of Aligning AI to Human Values." The State of AI Ethics Report 4, p. 180-183. 2021.