English
Related papers

Related papers: MarginGate: Sparse Margin-Triggered Verification f…

200 papers

While random demonstration labels barely hurt in-context learning (Min et al., 2022), we show that homogeneous labels--even semantically valid ones--collapse accuracy to <=12% across six models (Pythia, Llama, Qwen; 0.8B--8B) and four…

Machine Learning · Computer Science 2026-05-12 Ming Liu

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

Gating mechanisms have been widely utilized, from early models like LSTMs and Highway Networks to recent state space models, linear attention, and also softmax attention. Yet, existing literature rarely examines the specific effects of…

Computation and Language · Computer Science 2025-05-13 Zihan Qiu , Zekun Wang , Bo Zheng , Zeyu Huang , Kaiyue Wen , Songlin Yang , Rui Men , Le Yu , Fei Huang , Suozhi Huang , Dayiheng Liu , Jingren Zhou , Junyang Lin

This paper addresses the critical challenge of deriving interpretable confidence scores from generative language models (LLMs) when applied to multi-label content safety classification. While models like LLaMA Guard are effective for…

Computation and Language · Computer Science 2025-12-01 Anjaneya Praharaj , Jaykumar Kasundra

Deploying LLMs raises two coupled challenges: (1) monitoring--estimating where a model underperforms as traffic and domains drift--and (2) improvement--prioritizing data acquisition to close the largest performance gaps. We test whether an…

Computation and Language · Computer Science 2026-05-27 Pedro Memoli Buffa , Luciano Del Corro

We introduce obfuscation testing, a novel methodology for validating whether large language models detect structural market patterns through causal reasoning rather than temporal association. Testing three dealer hedging constraint patterns…

Statistical Finance · Quantitative Finance 2025-12-30 Christopher Regan , Ying Xie

Detection of level shifts in a noisy signal, or trend break detection, is a problem that appears in several research fields, from biophysics to optics and economics. Although many algorithms have been developed to deal with such problem,…

Signal Processing · Electrical Eng. & Systems 2019-02-19 Felipe Calliari , Gustavo C. Amaral , Michael Lunglmayr

Large language models (LLMs) are increasingly used for high-stakes decisions, yet their susceptibility to spurious features remains poorly characterized. We introduce ICE-Guard, a framework applying intervention consistency testing to…

Computation and Language · Computer Science 2026-03-20 Abhinaba Basu , Pavan Chakraborty

Large language models (LLMs) have demonstrated state-of-the-art performance across various tasks. However, the latency of inference and the large GPU memory consumption of LLMs restrict their deployment performance. Recently, there have…

Machine Learning · Computer Science 2024-02-29 Yi Zhang , Fei Yang , Shuang Peng , Fangyu Wang , Aimin Pan

Existing benchmarks for tool-augmented language models (TaLMs) lack fine-grained control over task difficulty and remain vulnerable to data contamination. We present FuncBenchGen, a unified, contamination-free framework that evaluates TaLMs…

Computation and Language · Computer Science 2026-02-10 Seiji Maekawa , Jackson Hassell , Pouya Pezeshkpour , Tom Mitchell , Estevam Hruschka

Auto-regressive decoding in Large Language Models (LLMs) is inherently memory-bound: every generation step requires loading the model weights and intermediate results from memory (e.g., High-Bandwidth Memory (HBM) for GPU servers), making…

Machine Learning · Computer Science 2026-05-13 Yuning Han , Yangchenchen Jin , Dylan Zhao , Jingwei Sun

Large Language Models (LLMs) often exhibit strong linguistic abilities while remaining unreliable on multi-step reasoning tasks, particularly when deployed without additional training or fine-tuning. In this work, we study inference-time…

Computation and Language · Computer Science 2026-03-24 Vinay Sharma , Manish Jain

Experiments conducted on open-access cloud-based IBM Quantum devices are presented for characterizing their fault tolerance using $[4,2,2]$-encoded gate sequences. Up to 100 logical gates are activated in the IBMQ Bogota and IBMQ Santiago…

Quantum Physics · Physics 2021-12-09 Rosie Cane , Daryus Chandra , Soon Xin Ng , Lajos Hanzo

We present a universal scheme of pulsed operations for the IBM oscillator-stabilized flux qubit comprising the CPHASE gate, single-qubit preparations and measurements. Based on numerical simulations, we argue that the error rates for these…

We present a practical system for privacy-aware large language model (LLM) inference that splits a transformer between a trusted local GPU and an untrusted cloud GPU, communicating only intermediate activations over the network. Our system…

Cryptography and Security · Computer Science 2026-02-20 Michael Cunningham

Coverage closure is the most time-consuming phase of hardware verification, and recent large language model (LLM)-based coding agents offer a promising approach to automated stimulus generation. However, prior LLM-based flows do not…

Hardware Architecture · Computer Science 2026-04-20 Vihaan Patel , Vidya Chhabria , Aman Arora

This thesis investigates the physics performance, trigger efficiency, and Field Programmable Gate Array (FPGA) implementation of machine learning (ML)-based algorithms for Lorentz-boosted $H\rightarrow b\bar{b}$ tagging within the CMS…

Instrumentation and Detectors · Physics 2025-06-02 Mila Bileska

The computational cost of training multimodal large language models (MLLMs) grows rapidly with the number of processed tokens. Existing efficiency methods mainly target inference via token reduction or merging, offering limited benefits…

Computer Vision and Pattern Recognition · Computer Science 2026-04-30 Chaoyu Li , Yogesh Kulkarni , Pooyan Fazli

Efficient and realistic error decoding is crucial for fault-tolerant quantum computation (FTQC) on near-term devices. While decoding is a classical post-processing task, its effectiveness depends on accurately modeling quantum noise, which…

Quantum Physics · Physics 2025-09-10 Yi Tian , Y. Zheng , Xiaoting Wang , Ching-Yi Lai

Large Language Models (LLMs) often rely on test-time scaling via parallel decoding (for example, 512 samples) to boost reasoning accuracy, but this incurs substantial compute. We introduce CoRefine, a confidence-guided self-refinement…

Artificial Intelligence · Computer Science 2026-02-10 Chen Jin , Ryutaro Tanno , Tom Diethe , Philip Teare