Variational Reasoning for Language Models episode artwork

EPISODE · Sep 30, 2025 · 22 MIN

Variational Reasoning for Language Models

from Daily Paper Cast · host Jingwen Liang, Gengyu Wang

🤗 Upvotes: 51 | cs.CL, cs.AI, cs.LG Authors: Xiangxin Zhou, Zichen Liu, Haonan Wang, Chao Du, Min Lin, Chongxuan Li, Liang Wang, Tianyu Pang Title: Variational Reasoning for Language Models Arxiv: http://arxiv.org/abs/2509.22637v1 Abstract: We introduce a variational reasoning framework for language models that treats thinking traces as latent variables and optimizes them through variational inference. Starting from the evidence lower bound (ELBO), we extend it to a multi-trace objective for tighter bounds and propose a forward-KL formulation that stabilizes the training of the variational posterior. We further show that rejection sampling finetuning and binary-reward RL, including GRPO, can be interpreted as local forward-KL objectives, where an implicit weighting by model accuracy naturally arises from the derivation and reveals a previously unnoticed bias toward easier questions. We empirically validate our method on the Qwen 2.5 and Qwen 3 model families across a wide range of reasoning tasks. Overall, our work provides a principled probabilistic perspective that unifies variational inference with RL-style methods and yields stable objectives for improving the reasoning ability of language models. Our code is available at https://github.com/sail-sg/variational-reasoning.

Episode metadata supplied by the publisher feed · Published Sep 30, 2025

🤗 Upvotes: 51 | cs.CL, cs.AI, cs.LG Authors: Xiangxin Zhou, Zichen Liu, Haonan Wang, Chao Du, Min Lin, Chongxuan Li, Liang Wang, Tianyu Pang Title: Variational Reasoning for Language Models Arxiv: http://arxiv.org/abs/2509.22637v1 Abstract: We introduce a variational reasoning framework for language models that treats thinking traces as latent variables and optimizes them through variational inference. Starting from the evidence lower bound (ELBO), we extend it to a multi-trace objective for tighter bounds and propose a forward-KL formulation that stabilizes the training of the variational posterior. We further show that rejection sampling finetuning and binary-reward RL, including GRPO, can be interpreted as local forward-KL objectives, where an implicit weighting by model accuracy naturally arises from the derivation and reveals a previously unnoticed bias toward easier questions. We empirically validate our method on the Qwen 2.5 and Qwen 3 model families across a wide range of reasoning tasks. Overall, our work provides a principled probabilistic perspective that unifies variational inference with RL-style methods and yields stable objectives for improving the reasoning ability of language models. Our code is available at https://github.com/sail-sg/variational-reasoning.

PodParley-generated summary based on available episode metadata and transcript content.

NOW PLAYING

Variational Reasoning for Language Models

0:00 22:33

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

No similar episodes found.

Frequently Asked Questions

How long is this episode of Daily Paper Cast?

This episode is 22 minutes long.

When was this Daily Paper Cast episode published?

This episode was published on September 30, 2025.

What is this episode about?

🤗 Upvotes: 51 | cs.CL, cs.AI, cs.LG Authors: Xiangxin Zhou, Zichen Liu, Haonan Wang, Chao Du, Min Lin, Chongxuan Li, Liang Wang, Tianyu Pang Title: Variational Reasoning for Language...

Can I download this Daily Paper Cast episode?

Yes, you can download this episode by clicking the download button on the episode player, or subscribe to the podcast in your preferred podcast app for automatic downloads.
URL copied to clipboard!