English
Related papers

Related papers: Entropy-Guided Loop: Achieving Reasoning through U…

200 papers

Multimodal reward models are crucial for aligning multimodal large language models with human preferences. Recent works have incorporated reasoning capabilities into these models, achieving promising results. However, training these models…

Artificial Intelligence · Computer Science 2026-02-03 Shidong Yang , Tongwen Huang , Hao Wen , Yong Wang , Li Chen , Xiangxiang Chu

Large Language Models (LLMs) that can express interpretable and calibrated uncertainty are crucial in high-stakes domains. While methods to compute uncertainty post-hoc exist, they are often sampling-based and therefore computationally…

Machine Learning · Computer Science 2026-03-09 Azza Jenane , Nassim Walha , Lukas Kuhn , Florian Buettner

With the rise of reasoning language models and test-time scaling methods as a paradigm for improving model performance, substantial computation is often required to generate multiple candidate sequences from the same prompt. This enables…

Machine Learning · Computer Science 2026-05-28 Daniel Scalena , Leonidas Zotos , Elisabetta Fersini , Malvina Nissim , Ahmet Üstün

Large language models achieve strong reasoning performance, yet existing decoding strategies either explore blindly (random sampling) or redundantly (independent multi-sampling). We propose Entropy-Tree, a tree-based decoding method that…

Computation and Language · Computer Science 2026-01-23 Longxuan Wei , Yubo Zhang , Zijiao Zhang , Zhihu Wang , Shiwan Zhao , Tianyu Huang , Huiting Zhao , Chenfei Liu , Shenao Zhang , Junchi Yan

Sequential recommender systems have achieved steady gains in offline accuracy, yet it remains unclear how close current models are to the intrinsic accuracy limit imposed by the data. A reliable, model-agnostic estimate of this ceiling…

Information Retrieval · Computer Science 2026-04-15 En Xu , Jingtao Ding , Yong Li

Large language models (LLMs) achieve remarkable generative performance, yet their output quality is dependent on the decoding strategy. While sampling-based methods (e.g., top-k, nucleus) and search-and-select based methods (e.g., beam…

Machine Learning · Computer Science 2026-05-12 Benjamin Patrick Evans , Sumitra Ganesh , Leo Ardon

We present Entropy Adaptive Decoding (EAD), a novel approach for efficient language model inference that dynamically switches between different-sized models based on prediction uncertainty. By monitoring rolling entropy in model logit…

Machine Learning · Computer Science 2025-02-12 Toby Simonds

Entropy minimization (EM) trains the model to concentrate even more probability mass on its most confident outputs. We show that this simple objective alone, without any labeled data, can substantially improve large language models' (LLMs)…

Machine Learning · Computer Science 2025-05-22 Shivam Agarwal , Zimin Zhang , Lifan Yuan , Jiawei Han , Hao Peng

Frontier reasoning models are produced by posttraining base language models with reinforcement learning. Recent work has challenged this by showing that sampling from a sharpened version of the base model's distribution, a so-called power…

Machine Learning · Computer Science 2026-05-29 Felix Zhou , Anay Mehrotra , Quanquan C. Liu

Large language models (LLMs) now exhibit strong multi-step reasoning abilities, but existing inference-time scaling methods remain computationally expensive, often relying on extensive sampling or external evaluators. We propose a…

Artificial Intelligence · Computer Science 2026-03-10 Nicolas Legrand , Kenneth Enevoldsen , Márton Kardos , Kristoffer Nielbo

Reasoning in Large Language Models incurs significant inference-time compute, yet the token-level information structure of reasoning traces remains underexplored. We observe that reasoning tokens split into two functional types: low-entropy…

Computation and Language · Computer Science 2026-05-06 Zhenyu Zhao , Sander Land , Daniel M. Bikel , Waseem Alshikh

The weak law of large numbers implies that, under mild assumptions on the source, the Renyi entropy per produced symbol converges (in probability) towards the Shannon entropy rate. This paper quantifies the speed of this convergence for…

Information Theory · Computer Science 2017-05-01 Maciej Skorski

Recent reasoning Large Language Models (LLMs) demonstrate remarkable problem-solving abilities but often generate long thinking traces whose utility is unclear. Our work aims to improve their efficiency, enabling them to reach high…

Computation and Language · Computer Science 2026-05-11 Xiang Liu , Xuming Hu , Xiaowen Chu , Eunsol Choi

The scientific method relies on the iterated processes of inference and inquiry. The inference phase consists of selecting the most probable models based on the available data; whereas the inquiry phase consists of using what is known about…

Machine Learning · Statistics 2015-05-19 N. K. Malakar , K. H. Knuth

In this work, we explore uncertainty estimation as a proxy for correctness in LLM-generated code. To this end, we adapt two state-of-the-art techniques from natural language generation -- one based on entropy and another on mutual…

Software Engineering · Computer Science 2025-07-02 Arindam Sharma , Cristina David

We introduce the Entropy-Driven Uncertainty Process Reward Model (EDU-PRM), a novel entropy-driven training framework for process reward modeling that enables dynamic, uncertainty-aligned segmentation of complex reasoning steps, eliminating…

Machine Learning · Computer Science 2026-03-10 Lang Cao , Renhong Chen , Yingtian Zou , Chao Peng , Huacong Xu , Yuxian Wang , Wu Ning , Qian Chen , Mofan Peng , Zijie Chen , Peishuo Su , Yitong Li

Reasoning is a key component of language understanding in Large Language Models. While Chain-of-Thought prompting enhances performance via explicit intermediate steps, it suffers from sufficient token overhead and a fixed reasoning…

Computation and Language · Computer Science 2025-11-18 Xinyuan Wang , Dongjie Wang , Wangyang Ying , Haoyue Bai , Nanxu Gong , Sixun Dong , Kunpeng Liu , Yanjie Fu

Chain-of-thought (CoT) reasoning improves large language models (LLMs) on difficult tasks, but it also makes inference expensive because every intermediate step must be generated as a discrete token. Latent reasoning reduces visible token…

Computation and Language · Computer Science 2026-05-11 Xuan Li , Yining Wang , Yuchen Liu , Guanjun Liu , Delai Qiu , Shengping Liu , Jiaen Liang , Wei Huang , Jun Yu , Junnan Zhu

Large language models (LLMs) and multimodal LLMs (MLL-Ms) excel at chain-of-thought reasoning but face distribution shift at test-time and a lack of verifiable supervision. Recent test-time reinforcement learning (TTRL) methods derive…

Computation and Language · Computer Science 2026-03-09 Jianghao Wu , Yasmeen George , Jin Ye , Yicheng Wu , Daniel F. Schmidt , Jianfei Cai

Chain-of-thought (CoT) prompting enhances reasoning in large language models (LLMs) but often leads to verbose and redundant outputs, thus increasing inference cost. We hypothesize that many reasoning steps are unnecessary for producing…

Computation and Language · Computer Science 2025-09-30 Xin Liu , Lu Wang