English
Related papers

Related papers: Lost in the Noise: How Reasoning Models Fail with …

200 papers

Noisy labels are inevitable in large real-world datasets. In this work, we explore an area understudied by previous works -- how the network's architecture impacts its robustness to noisy labels. We provide a formal framework connecting the…

Machine Learning · Computer Science 2021-11-30 Jingling Li , Mozhi Zhang , Keyulu Xu , John P. Dickerson , Jimmy Ba

With the explosion of massive, widely available unlabeled data in the past years, finding label and time efficient, robust learning algorithms has become ever more important in theory and in practice. We study the paradigm of active…

Machine Learning · Computer Science 2020-01-17 Max Hopkins , Daniel Kane , Shachar Lovett , Gaurav Mahajan

Extensive studies have shown that deep learning models are vulnerable to adversarial and natural noises, yet little is known about model robustness on noises caused by different system implementations. In this paper, we for the first time…

Machine Learning · Computer Science 2023-07-04 Yan Wang , Yuhang Li , Ruihao Gong , Aishan Liu , Yanfei Wang , Jian Hu , Yongqiang Yao , Yunchen Zhang , Tianzi Xiao , Fengwei Yu , Xianglong Liu

Retrieval Augmented Generation (RAG), a paradigm that integrates external contextual information with large language models (LLMs) to enhance factual accuracy and relevance, has emerged as a pivotal area in generative AI. The LLMs used in…

Computation and Language · Computer Science 2024-09-17 Xuan-Phi Nguyen , Shrey Pandit , Senthil Purushwalkam , Austin Xu , Hailin Chen , Yifei Ming , Zixuan Ke , Silvio Savarese , Caiming Xong , Shafiq Joty

Large language models (LLMs) are being increasingly adopted in the software engineering domain, yet the robustness of their grasp on core software design concepts remains unclear. We conduct an empirical study to systematically evaluate…

Software Engineering · Computer Science 2025-12-30 Mootez Saad , Boqi Chen , José Antonio Hernández López , Dániel Varró , Tushar Sharma

Retrieval-augmented generation (RAG) enhances language models by integrating external knowledge, but its effectiveness is highly dependent on system configuration. Improper retrieval settings can degrade performance, making RAG less…

Computation and Language · Computer Science 2025-07-17 Jennifer Hsia , Afreen Shaikh , Zhiruo Wang , Graham Neubig

Large language models (LLMs) are increasingly used in social science simulations. While their performance on reasoning and optimization tasks has been extensively evaluated, less attention has been paid to their ability to simulate human…

Computational Engineering, Finance, and Science · Computer Science 2025-08-25 Yuanjun Feng , Vivek Choudhary , Yash Raj Shrestha

Reinforcement Learning with Verifiable Rewards (RLVR) has advanced LLM reasoning, but remains constrained by inefficient exploration under limited rollout budgets, leading to low sampling success and unstable training in complex tasks. We…

Machine Learning · Computer Science 2026-04-21 Yiju Guo , Tianyi Hu , Zexu Sun , Yankai Lin

Risk assessment tools are widely used around the country to inform decision making within the criminal justice system. Recently, considerable attention has been devoted to the question of whether such tools may suffer from racial bias. In…

Methodology · Statistics 2020-04-01 Riccardo Fogliato , Max G'Sell , Alexandra Chouldechova

Large language models (LLMs) generate outputs by utilizing extensive context, which often includes redundant information from prompts, retrieved passages, and interaction history. In critical applications, it is vital to identify which…

Computation and Language · Computer Science 2026-02-03 Poushali Sengupta , Shashi Raj Pandey , Sabita Maharjan , Frank Eliassen

The emergence of large language models has enabled sophisticated multi-agent systems, yet coordinating their reasoning capabilities through prompt engineering remains challenging. We present a theoretically-grounded framework for dynamic…

Multiagent Systems · Computer Science 2025-10-02 Hassen Dhrif

The performance of speech processing models trained on clean speech drops significantly in noisy conditions. Training with noisy datasets alleviates the problem, but procuring such datasets is not always feasible. Noisy speech simulation…

Sound · Computer Science 2023-05-23 Leander Melroy Maben , Zixun Guo , Chen Chen , Utkarsh Chudiwal , Chng Eng Siong

Large language models (LLMs) have the potential to transform medicine, but real-world clinical scenarios contain extraneous information that can hinder performance. The rise of assistive technologies like ambient dictation, which…

Computation and Language · Computer Science 2025-04-03 Krithik Vishwanath , Anton Alyakin , Daniel Alexander Alber , Jin Vivian Lee , Douglas Kondziolka , Eric Karl Oermann

This paper addresses the issue of active speaker detection (ASD) in noisy environments and formulates a robust active speaker detection (rASD) problem. Existing ASD approaches leverage both audio and visual modalities, but non-speech sounds…

Multimedia · Computer Science 2024-04-02 Siva Sai Nagender Vasireddy , Chenxu Zhang , Xiaohu Guo , Yapeng Tian

Machine learning models are routinely used to support decisions that affect individuals -- be it to screen a patient for a serious illness or to gauge their response to treatment. In these tasks, we are limited to learning models from…

Machine Learning · Computer Science 2025-06-10 Sujay Nagaraj , Yang Liu , Flavio P. Calmon , Berk Ustun

LLMs have made significant progress in the field of mathematical reasoning, but whether they have true the mathematical understanding ability is still controversial. To explore this issue, we propose a new perturbation framework to evaluate…

Artificial Intelligence · Computer Science 2025-11-12 Zhishen Sun , Guang Dai , Ivor Tsang , Haishan Ye

As large language models (LLMs) evolve into autonomous agents capable of acting in open-ended environments, ensuring behavioral alignment with human values becomes a critical safety concern. Existing benchmarks, focused on static,…

Computation and Language · Computer Science 2026-03-10 Weixiang Zhao , Haozhen Li , Yanyan Zhao , xuda zhi , Yongbo Huang , Hao He , Bing Qin , Ting Liu

The evolution of Large Language Models (LLMs) into autonomous agents necessitates the management of extensive, dynamic contexts. Current benchmarks, however, remain largely static, relying on passive retrieval tasks that fail to simulate…

Computation and Language · Computer Science 2026-02-02 Shicheng Fang , Yuxin Wang , Xiaoran Liu , Jiahao Lu , Chuanyuan Tan , Xinchi Chen , Yining Zheng , Xuanjing Huang , Xipeng Qiu

Reasoning in large language models has long been a central research focus, and recent studies employing reinforcement learning (RL) have introduced diverse methods that yield substantial performance gains with minimal or even no external…

Supervised machine learning models often associate irrelevant nuisance factors with the prediction target, which hurts generalization. We propose a framework for training robust neural networks that induces invariance to nuisances through…

Machine Learning · Computer Science 2019-12-03 Ayush Jaiswal , Rob Brekelmans , Daniel Moyer , Greg Ver Steeg , Wael AbdAlmageed , Premkumar Natarajan