Research paper: [2304.03279] Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark
Quote: “To both guide progress on text-based agents and encourage them to be more moral, we propose the Measuring Agents’ Competence & Harmfulness In A Vast Environment of Long-horizon Language Interactions (MACHIAVELLI) benchmark. Our environment, detailed in Table 1, is based on human-written, text-based Choose-Your-Own-Adventure games from choiceofgames.com.”