Copertina

When Models Ignore Definitions: Measuring Semantic Override Hallucinations in LLM Reasoning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Thota, Yogeswar Reddy, Rafatirad, Setareh, Houman, Homayoun, Nikoubin, Tooraj
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Hardware Architecture
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Human-AI Interaction: Evaluating LLM Reasoning on Digital Logic Circuit included Graph Problems, in terms of creativity in design and analysis
di: Thota, Yogeswar Reddy, et al.
Pubblicazione: (2026)

Iterative LLM-Based Assertion Generation Using Syntax-Semantic Representations for Functional Coverage-Guided Verification
di: Wang, Yonghao, et al.
Pubblicazione: (2026)

CoverAssert: Iterative LLM Assertion Generation Driven by Functional Coverage via Syntax-Semantic Representations
di: Wang, Yonghao, et al.
Pubblicazione: (2026)

Analog Solver Circuit for Linear Symmetric Positive-Definite Systems at a Complexity Independent of Matrix Size
di: Abdelaleim, Osama, et al.
Pubblicazione: (2025)

HaVen: Hallucination-Mitigated LLM for Verilog Code Generation Aligned with HDL Engineers
di: Yang, Yiyao, et al.
Pubblicazione: (2025)

SemanticBBV: A Semantic Signature for Cross-Program Knowledge Reuse in Microarchitecture Simulation
di: Liu, Zhenguo, et al.
Pubblicazione: (2025)

Calibrating DRAMPower Model for HPC: A Runtime Perspective from Real-Time Measurements
di: Shi, Xinyu, et al.
Pubblicazione: (2024)

SpeedLLM: An FPGA Co-design of Large Language Model Inference Accelerator
di: Wang, Peipei, et al.
Pubblicazione: (2025)

SpecLLM: Exploring Generation and Review of VLSI Design Specification with Large Language Model
di: Li, Mengming, et al.
Pubblicazione: (2024)

LintLLM: An Open-Source Verilog Linting Framework Based on Large Language Models
di: Fang, Zhigang, et al.
Pubblicazione: (2025)

When Forgetting Builds Reliability: LLM Unlearning for Reliable Hardware Code Generation
di: Liang, Yiwen, et al.
Pubblicazione: (2025)

ATLAAS: Automatic Tensor-Level Abstraction of Accelerator Semantics
di: Gao, Ruijie, et al.
Pubblicazione: (2026)

FPGA-based Hyrbid Memory Emulation System
di: Wen, Fei, et al.
Pubblicazione: (2020)

EdgeLLM: A Highly Efficient CPU-FPGA Heterogeneous Edge Accelerator for Large Language Models
di: Huang, Mingqiang, et al.
Pubblicazione: (2024)

DECA: A Near-Core LLM Decompression Accelerator Grounded on a 3D Roofline Model
di: Gerogiannis, Gerasimos, et al.
Pubblicazione: (2025)

OpenLLM-RTL: Open Dataset and Benchmark for LLM-Aided Design RTL Generation
di: Liu, Shang, et al.
Pubblicazione: (2025)

When NPUs Are Not Always Faster: A Stage-Level Analysis of Mobile LLM Inference
di: Li, Pu, et al.
Pubblicazione: (2026)

E2AFS: Energy-Efficient Approximate Floating Point Square Rooter for Error Tolerant Computing
di: Goyal, Prateek, et al.
Pubblicazione: (2026)

VitaLLM: A Versatile, Ultra-Compact Ternary LLM Accelerator with Dependency-Aware Scheduling
di: Lin, Zi-Wei, et al.
Pubblicazione: (2026)

LLM-PRISM: Characterizing Silent Data Corruption from Permanent GPU Faults in LLM Training
di: Tyagi, Abhishek, et al.
Pubblicazione: (2026)

VitaLLM: A Versatile and Tiny Accelerator for Mixed-Precision LLM Inference on Edge Devices
di: Lin, Zi-Wei, et al.
Pubblicazione: (2026)

Cambricon-LLM: A Chiplet-Based Hybrid Architecture for On-Device Inference of 70B LLM
di: Yu, Zhongkai, et al.
Pubblicazione: (2024)

ITERA-LLM: Boosting Sub-8-Bit Large Language Model Inference via Iterative Tensor Decomposition
di: Zheng, Keran, et al.
Pubblicazione: (2025)

When Pipelined In-Memory Accelerators Meet Spiking Direct Feedback Alignment: A Co-Design for Neuromorphic Edge Computing
di: Ren, Haoxiong, et al.
Pubblicazione: (2025)

HLSPilot: LLM-based High-Level Synthesis
di: Xiong, Chenwei, et al.
Pubblicazione: (2024)

A Systematic Characterization of LLM Inference on GPUs
di: Wang, Haonan, et al.
Pubblicazione: (2025)

LIMINAL: Exploring The Frontiers of LLM Decode Performance
di: Davies, Michael, et al.
Pubblicazione: (2025)

BoolE: Exact Symbolic Reasoning via Boolean Equality Saturation
di: Yin, Jiaqi, et al.
Pubblicazione: (2025)

SkyByte: Architecting an Efficient Memory-Semantic CXL-based SSD with OS and Hardware Co-design
di: Zhang, Haoyang, et al.
Pubblicazione: (2025)

Fair and Square: Replacing One Real Multiplication with a Single Square and One Complex Multiplication with Three Squares When Performing Matrix Multiplication and Convolutions
di: Liguori, Vincenzo
Pubblicazione: (2026)

SPARQLe: Sub-Precision Activation Representation for Quantized LLM Inference
di: Parvathy, Aradhana Mohan, et al.
Pubblicazione: (2026)

LLM-Powered Code Analysis and Optimization for Gaussian Splatting Kernels
di: Hu, Yi, et al.
Pubblicazione: (2025)

TerEffic: Highly Efficient Ternary LLM Inference on FPGA
di: Yin, Chenyang, et al.
Pubblicazione: (2025)

Uncertainty-Guided Live Measurement Sequencing for Fast SAR ADC Linearity Testing
di: Schey, Thorben, et al.
Pubblicazione: (2025)

Empirical Measurements of AI Training Power Demand on a GPU-Accelerated Node
di: Latif, Imran, et al.
Pubblicazione: (2024)

Retrieve, Schedule, Reflect: LLM Agents for Chip QoR Optimization
di: ouyang, Yikang, et al.
Pubblicazione: (2026)

From Natural Language to Silicon: The Representation Bottleneck in LLM Hardware Design
di: Fu, Weimin, et al.
Pubblicazione: (2026)

LLM-Aided Testbench Generation and Bug Detection for Finite-State Machines
di: Bhandari, Jitendra, et al.
Pubblicazione: (2024)

LIMCA: LLM for Automating Analog In-Memory Computing Architecture Design Exploration
di: Vungarala, Deepak, et al.
Pubblicazione: (2025)

Titanus: Enabling KV Cache Pruning and Quantization On-the-Fly for LLM Acceleration
di: Chen, Peilin, et al.
Pubblicazione: (2025)