Reaching Beyond the Mode: RL for Distributional Reasoning in Language Models
This addresses the need for more robust and efficient distributional reasoning in language models for real-world applications like medical diagnosis and ambiguous question answering, representing a novel method rather than an incremental improvement.
The paper tackles the problem of language models collapsing answer distributions to a single mode, which is insufficient for tasks with multiple valid answers or uncertainty, by proposing a multi-answer reinforcement learning approach that enables models to generate multiple candidate answers in a single forward pass. The result shows improved diversity, coverage, and calibration scores across benchmarks, with models requiring fewer tokens and achieving higher accuracy on coding tasks compared to baselines.
Given a question, a language model (LM) implicitly encodes a distribution over possible answers. In practice, post-training procedures for LMs often collapse this distribution onto a single dominant mode. While this is generally not a problem for benchmark-style evaluations that assume one correct answer, many real-world tasks inherently involve multiple valid answers or irreducible uncertainty. Examples include medical diagnosis, ambiguous question answering, and settings with incomplete information. In these cases, we would like LMs to generate multiple plausible hypotheses, ideally with confidence estimates for each one, and without computationally intensive repeated sampling to generate non-modal answers. This paper describes a multi-answer reinforcement learning approach for training LMs to perform distributional reasoning over multiple answers during inference. We modify the RL objective to enable models to explicitly generate multiple candidate answers in a single forward pass, internalizing aspects of inference-time search into the model's generative process. Across question-answering, medical diagnostic, and coding benchmarks, we observe improved diversity, coverage, and set-level calibration scores compared to single answer trained baselines. Models trained with our approach require fewer tokens to generate multiple answers than competing approaches. On coding tasks, they are also substantially more accurate. These results position multi-answer RL as a principled and compute-efficient alternative to inference-time scaling procedures such as best-of-k. Code and more information can be found at https://multi-answer-rl.github.io/.