English
Related papers

Related papers: ALIEN: Aligned Entropy Head for Improving Uncertai…

200 papers

Compressed Deep Learning (DL) models are essential for deployment in resource-constrained environments. But their performance often lags behind their large-scale counterparts. To bridge this gap, we propose Alignment Adapter (AlAd): a…

Machine Learning · Computer Science 2026-02-17 Rohit Raj Rai , Abhishek Dhaka , Amit Awekar

Current pre-training works in natural language generation pay little attention to the problem of exposure bias on downstream tasks. To address this issue, we propose an enhanced multi-flow sequence to sequence pre-training and fine-tuning…

Computation and Language · Computer Science 2020-06-09 Dongling Xiao , Han Zhang , Yukun Li , Yu Sun , Hao Tian , Hua Wu , Haifeng Wang

Existing methods to enhance the reasoning capability of large language models predominantly rely on supervised fine-tuning (SFT) followed by reinforcement learning (RL) on reasoning-specific data. These approaches critically depend on…

Machine Learning · Computer Science 2025-05-20 Qingyang Zhang , Haitao Wu , Changqing Zhang , Peilin Zhao , Yatao Bian

With the rapid development of large language models (LLMs) and ever-evolving practical requirements, finding an efficient and effective alignment method has never been more critical. However, the tension between the complexity of current…

Computation and Language · Computer Science 2024-11-05 Jiaming Ji , Boyuan Chen , Hantao Lou , Donghai Hong , Borong Zhang , Xuehai Pan , Juntao Dai , Tianyi Qiu , Yaodong Yang

Reinforcement learning (RL) has substantially improved the ability of large language model (LLM) agents to interact with environments and solve multi-turn tasks. However, effective agentic RL remains challenging: sparse outcome-only rewards…

There is a family of label modification approaches including self and non-self label correction (LC), and output regularisation. They are widely used for training robust deep neural networks (DNNs), but have not been mathematically and…

Machine Learning · Computer Science 2022-09-07 Xinshao Wang , Yang Hua , Elyor Kodirov , Sankha Subhra Mukherjee , David A. Clifton , Neil M. Robertson

In this paper, we study the problem of uncertainty estimation and calibration for LLMs. We begin by formulating the uncertainty estimation problem, a relevant yet underexplored area in existing literature. We then propose a supervised…

Machine Learning · Computer Science 2024-10-24 Linyu Liu , Yu Pan , Xiaocheng Li , Guanting Chen

Numerous real-world decisions rely on machine learning algorithms and require calibrated uncertainty estimates. However, modern methods often yield overconfident, uncalibrated predictions. The dominant approach to quantifying the…

Explanation-guided learning (EGL) has shown promise in aligning model predictions with interpretable reasoning, particularly in computer vision tasks. However, most approaches rely on external annotations or heuristic-based segmentation to…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Dongsheng Hong , Chao Chen , Yanhui Chen , Shanshan Lin , Zhihao Chen , Xiangwen Liao

Named Entity Recognition (NER) serves as a foundational component in many natural language processing (NLP) pipelines. However, current NER models typically output a single predicted label sequence without any accompanying measure of…

Computation and Language · Computer Science 2026-01-27 Matthew Singer , Srijan Sengupta , Karl Pazdernik

In this paper, online linear regression in environments corrupted by non-Gaussian noise (especially heavy-tailed noise) is addressed. In such environments, the error between the system output and the label also does not follow a Gaussian…

Information Theory · Computer Science 2021-05-13 Sajjad Bahrami , Ertem Tuncel

Language prediction is constrained by informational entropy intrinsic to language, such that there exists a limit to how accurate any language model can become and equivalently a lower bound to language compression. The most efficient…

Computation and Language · Computer Science 2025-11-14 Benjamin L. Badger , Matthew Neligeorge

Dense retrieval systems increasingly need to handle complex queries. In many realistic settings, users express intent through long instructions or task-specific descriptions, while target documents remain relatively simple and static. This…

Information Retrieval · Computer Science 2026-04-07 Seiji Maekawa , Moin Aminnaseri , Pouya Pezeshkpour , Estevam Hruschka

Deep neural networks are highly susceptible to overfitting noisy labels, which leads to degraded performance. Existing methods address this issue by employing manually defined criteria, aiming to achieve optimal partitioning in each…

Computer Vision and Pattern Recognition · Computer Science 2025-02-04 Wenzhen Zhang , Debo Cheng , Guangquan Lu , Bo Zhou , Jiaye Li , Shichao Zhang

Off-policy problems such as policy staleness and training--inference mismatch have become a major bottleneck for training stability and further exploration in LLM RL. The distribution gap between the inference and updated policies grows…

Machine Learning · Computer Science 2026-05-19 Chenlu Ye , Xuanchang Zhang , Yifan Hao , Zhou Yu , Ziji Zhang , Abhinav Gullapalli , Hao Chen , Jing Huang , Tong Zhang

Large language models for subjectivity analysis are typically trained with aggregated labels, which compress variations in human judgment into a single supervision signal. This paradigm overlooks the intrinsic uncertainty of low-agreement…

Computation and Language · Computer Science 2026-05-14 Junyu Lu , Deyi Ji , Xuanyi Liu , Lanyun Zhu , Bo Xu , Liang Yang , Xian-Sheng Hua , Hongfei Lin

The objectives that Large Language Models (LLMs) implicitly optimize remain dangerously opaque, making trustworthy alignment and auditing a grand challenge. While Inverse Reinforcement Learning (IRL) can infer reward functions from…

Machine Learning · Computer Science 2025-10-09 Matthieu Bou , Nyal Patel , Arjun Jagota , Satyapriya Krishna , Sonali Parbhoo

The use of Large Language Models (LLMs) for reasoning and planning tasks has drawn increasing attention in Artificial Intelligence research. Despite their remarkable progress, these models still exhibit limitations in multi-step inference…

Artificial Intelligence · Computer Science 2026-01-21 Murilo da Luz , Bruno Brandão , Luana Martins , Gustavo Oliveira , Bryan de Oliveira , Luckeciano Melo , Telma Soares

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

Large language models (LLMs) remain unreliable for global enterprise applications due to substantial performance gaps between high-resource and mid/low-resource languages, driven by English-centric pretraining and internal reasoning biases.…

Computation and Language · Computer Science 2025-10-28 Amit Agarwal , Hansa Meghwani , Hitesh Laxmichand Patel , Tao Sheng , Sujith Ravi , Dan Roth