English
Related papers

Related papers: Entropy-Guided Token Dropout: Training Autoregress…

200 papers

Agents trained with deep reinforcement learning algorithms are capable of performing highly complex tasks including locomotion in continuous environments. We investigate transferring the learning acquired in one task to a set of previously…

Machine Learning · Computer Science 2024-03-06 Suzan Ece Ada , Emre Ugur , H. Levent Akin

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

On-policy distillation is a promising approach for transferring knowledge between language models, where a student learns from dense token-level signals along its own trajectories. This framework typically uses reverse KL divergence,…

Machine Learning · Computer Science 2026-05-25 Woogyeol Jin , Taywon Min , Yongjin Yang , Swanand Ravindra Kadhe , Yi Zhou , Dennis Wei , Nathalie Baracaldo , Kimin Lee

Large Language Models (LLMs) deployed in real-world settings increasingly face the need to unlearn sensitive, outdated, or proprietary information. Existing unlearning methods typically formulate forgetting and retention as a regularized…

Computation and Language · Computer Science 2025-10-28 Taha Entesari , Arman Hatami , Rinat Khaziev , Anil Ramakrishna , Mahyar Fazlyab

Language models (LMs) are trained on billions of tokens in an attempt to recover the true language distribution. Still, vanilla random sampling from LMs yields low quality generations. Decoding algorithms attempt to restrict the LM…

Machine Learning · Computer Science 2026-01-06 Kareem Ahmed , Sameer Singh

Semisupervised text classification has become a major focus of research over the past few years. Hitherto, most of the research has been based on supervised learning, but its main drawback is the unavailability of labeled data samples in…

Machine Learning · Computer Science 2021-11-17 Shivani Malhotra , Vinay Kumar , Alpana Agarwal

Reasoning models often outperform smaller models but at 3--5$\times$ higher cost and added latency. We present entropy-guided refinement: a lightweight, test-time loop that uses token-level uncertainty to trigger a single, targeted…

Artificial Intelligence · Computer Science 2025-09-03 Andrew G. A. Correa , Ana C. H de Matos

Large language models (LLMs) in research and development toolchains produce output that triggers attribution of agency and understanding -- a cognitive illusion that degrades verification behavior and trust calibration. No existing…

Software Engineering · Computer Science 2026-04-10 Marek Miller

Large language model pretraining is compute-intensive, yet many tokens contribute marginally to learning, resulting in inefficiency. We introduce Efficient Selective Language Modeling (ESLM), a risk-aware algorithm that improves training…

Machine Learning · Computer Science 2025-05-27 Melis Ilayda Bal , Volkan Cevher , Michael Muehlebach

Large Language Models (LLMs) have demonstrated impressive performance across various tasks. However, current training approaches combine standard cross-entropy loss with extensive data, human feedback, or ad hoc methods to enhance…

Computation and Language · Computer Science 2024-12-16 Daniele Rege Cambrin , Giuseppe Gallipoli , Irene Benedetto , Luca Cagliero , Paolo Garza

Small language models (SLMs) have been increasingly deployed in edge devices and other resource-constrained settings. However, these models make confident mispredictions and produce unstable output, making them risky for factual and…

Artificial Intelligence · Computer Science 2026-04-07 Adeyemi Adeseye , Aisvarya Adeseye , Hannu Tenhunen , Jouni Isoaho

An important problem in training deep networks with high capacity is to ensure that the trained network works well when presented with new inputs outside the training dataset. Dropout is an effective regularization technique to boost the…

Computer Vision and Pattern Recognition · Computer Science 2017-12-06 Mostafa Rahmani , George Atia

The pervasiveness of proprietary language models has raised critical privacy concerns, necessitating advancements in private inference (PI), where computations are performed directly on encrypted data without revealing users' sensitive…

Machine Learning · Computer Science 2025-01-10 Nandan Kumar Jha , Brandon Reagen

Entropy regularization is a standard technique in reinforcement learning (RL) to enhance exploration, yet it yields negligible effects or even degrades performance in Large Language Models (LLMs). We attribute this failure to the cumulative…

Computation and Language · Computer Science 2026-02-04 Chao Huang , Yujing Lu , Quangang Li , Shenghe Wang , Yan Wang , Yueyang Zhang , Long Xia , Jiashu Zhao , Zhiyuan Sun , Daiting Shi , Tingwen Liu

Dropout is an effective strategy for the regularization of deep neural networks. Applying tabu to the units that have been dropped in the recent epoch and retaining them for training ensures diversification in dropout. In this paper, we…

The advancement of Large Reasoning Models (LRMs) has catalyzed a paradigm shift from reactive ``fast thinking'' text generation to systematic, step-by-step ``slow thinking'' reasoning, unlocking state-of-the-art performance in complex…

Artificial Intelligence · Computer Science 2026-05-25 Junyao Yang , Chen Qian , Kun Wang , Linfeng Zhang , Quanshi Zhang , Yong Liu , Dongrui Liu

Data augmentation (DA) has been widely used to improve the generalization of deep neural networks. While existing DA methods have proven effective, they often rely on augmentation operations with random magnitudes to each sample. However,…

Computer Vision and Pattern Recognition · Computer Science 2024-09-11 Suorong Yang , Furao Shen , Jian Zhao

Supervised fine-tuning (SFT) followed by reinforcement learning (RL) has become a standard post-training paradigm for large language models. This paradigm provides a cold-start for RL exploration, avoiding the inefficiency of pure RL where…

Artificial Intelligence · Computer Science 2026-05-29 Qi Liu , Mingdi Sun , Yongyi He , Zhi Zheng , Tong Xu , Yi Zheng , Zhefeng Wang , Enhong Chen

Recursive learning -- where models are trained on data generated by previous versions of themselves -- is increasingly common in large language models, autonomous agents, and self-supervised systems. However, standard performance metrics…

Machine Learning · Computer Science 2026-05-20 Zhipeng Zhang

In this paper, we explore various approaches for semi supervised learning in an end to end automatic speech recognition (ASR) framework. The first step in our approach involves training a seed model on the limited amount of labelled data.…

Audio and Speech Processing · Electrical Eng. & Systems 2019-08-15 Subhadeep Dey , Petr Motlicek , Trung Bui , Franck Dernoncourt