Improving alignment of dialogue agents via targeted human judgements
This work addresses alignment challenges for dialogue agents, making them safer and more reliable for users, though it is incremental with specific improvements to existing methods.
The authors tackled the problem of aligning dialogue agents to be more helpful, correct, and harmless by introducing Sparrow, which uses targeted human judgements and evidence-based reinforcement learning, resulting in 78% factual support and only 8% rule violations under probing.
We present Sparrow, an information-seeking dialogue agent trained to be more helpful, correct, and harmless compared to prompted language model baselines. We use reinforcement learning from human feedback to train our models with two new additions to help human raters judge agent behaviour. First, to make our agent more helpful and harmless, we break down the requirements for good dialogue into natural language rules the agent should follow, and ask raters about each rule separately. We demonstrate that this breakdown enables us to collect more targeted human judgements of agent behaviour and allows for more efficient rule-conditional reward models. Second, our agent provides evidence from sources supporting factual claims when collecting preference judgements over model statements. For factual questions, evidence provided by Sparrow supports the sampled response 78% of the time. Sparrow is preferred more often than baselines while being more resilient to adversarial probing by humans, violating our rules only 8% of the time when probed. Finally, we conduct extensive analyses showing that though our model learns to follow our rules it can exhibit distributional biases.