![[2603.17839] How do LLMs Compute Verbal Confidence](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
Llms
[2603.17839] How do LLMs Compute Verbal Confidence
Abstract page for arXiv paper 2603.17839: How do LLMs Compute Verbal Confidence
arXiv - AI
·
4 min
·
Large Language Models
GPT, Claude, Gemini, and other LLMs
Top This Week
Llms
[2603.15970] 100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models
Abstract page for arXiv paper 2603.15970: 100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight...
arXiv - AI
·
4 min
·
Llms
[2603.10062] Multi-Agent Memory from a Computer Architecture Perspective: Visions and Challenges Ahead
Abstract page for arXiv paper 2603.10062: Multi-Agent Memory from a Computer Architecture Perspective: Visions and Challenges Ahead
arXiv - AI
·
3 min
·
All Content
Llms
[2603.20314] VGS-Decoding: Visual Grounding Score Guided Decoding for Hallucination Mitigation in Medical VLMs
Abstract page for arXiv paper 2603.20314: VGS-Decoding: Visual Grounding Score Guided Decoding for Hallucination Mitigation in Medical VLMs
arXiv - Machine Learning
·
3 min
·
Llms
[2603.20219] Thinking into the Future: Latent Lookahead Training for Transformers
Abstract page for arXiv paper 2603.20219: Thinking into the Future: Latent Lookahead Training for Transformers
arXiv - Machine Learning
·
4 min
·
Llms
[2603.20218] An experimental study of KV cache reuse strategies in chunk-level caching systems
Abstract page for arXiv paper 2603.20218: An experimental study of KV cache reuse strategies in chunk-level caching systems
arXiv - Machine Learning
·
3 min
·
Llms
[2603.20215] Multi-Agent Debate with Memory Masking
Abstract page for arXiv paper 2603.20215: Multi-Agent Debate with Memory Masking
arXiv - Machine Learning
·
4 min
·
Llms
[2603.20212] Fast-Slow Thinking RM: Efficient Integration of Scalar and Generative Reward Models
Abstract page for arXiv paper 2603.20212: Fast-Slow Thinking RM: Efficient Integration of Scalar and Generative Reward Models
arXiv - Machine Learning
·
3 min
·
Llms
[2603.20217] Expected Reward Prediction, with Applications to Model Routing
Abstract page for arXiv paper 2603.20217: Expected Reward Prediction, with Applications to Model Routing
arXiv - Machine Learning
·
4 min
·
Llms
[2603.22206] Chimera: Latency- and Performance-Aware Multi-agent Serving for Heterogeneous LLMs
Abstract page for arXiv paper 2603.22206: Chimera: Latency- and Performance-Aware Multi-agent Serving for Heterogeneous LLMs
arXiv - Machine Learning
·
4 min
·
Llms
[2603.22184] Revisiting Quantum Code Generation: Where Should Domain Knowledge Live?
Abstract page for arXiv paper 2603.22184: Revisiting Quantum Code Generation: Where Should Domain Knowledge Live?
arXiv - Machine Learning
·
4 min
·
Llms
[2603.22161] Causal Evidence that Language Models use Confidence to Drive Behavior
Abstract page for arXiv paper 2603.22161: Causal Evidence that Language Models use Confidence to Drive Behavior
arXiv - Machine Learning
·
4 min
·
Llms
[2603.22154] dynActivation: A Trainable Activation Family for Adaptive Nonlinearity
Abstract page for arXiv paper 2603.22154: dynActivation: A Trainable Activation Family for Adaptive Nonlinearity
arXiv - Machine Learning
·
3 min
·
Llms
[2603.22017] AdditiveLLM2: A Multi-modal Large Language Model for Additive Manufacturing
Abstract page for arXiv paper 2603.22017: AdditiveLLM2: A Multi-modal Large Language Model for Additive Manufacturing
arXiv - Machine Learning
·
3 min
·
Llms
[2603.21972] Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe
Abstract page for arXiv paper 2603.21972: Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe
arXiv - Machine Learning
·
4 min
·
Llms
[2603.21862] Holistic Scaling Laws for Optimal Mixture-of-Experts Architecture Optimization
Abstract page for arXiv paper 2603.21862: Holistic Scaling Laws for Optimal Mixture-of-Experts Architecture Optimization
arXiv - Machine Learning
·
4 min
·
Llms
[2603.21705] Data-Free Layer-Adaptive Merging via Fisher Information for Long-to-Short Reasoning LLMs
Abstract page for arXiv paper 2603.21705: Data-Free Layer-Adaptive Merging via Fisher Information for Long-to-Short Reasoning LLMs
arXiv - Machine Learning
·
4 min
·
Llms
[2603.21584] SSAM: Singular Subspace Alignment for Merging Multimodal Large Language Models
Abstract page for arXiv paper 2603.21584: SSAM: Singular Subspace Alignment for Merging Multimodal Large Language Models
arXiv - Machine Learning
·
4 min
·
Llms
[2603.21567] Kolmogorov Complexity Bounds for LLM Steganography and a Perplexity-Based Detection Proxy
Abstract page for arXiv paper 2603.21567: Kolmogorov Complexity Bounds for LLM Steganography and a Perplexity-Based Detection Proxy
arXiv - Machine Learning
·
3 min
·
Llms
[2603.21534] Generalization Limits of In-Context Operator Networks for Higher-Order Partial Differential Equations
Abstract page for arXiv paper 2603.21534: Generalization Limits of In-Context Operator Networks for Higher-Order Partial Differential Equ...
arXiv - Machine Learning
·
3 min
·
Llms
[2603.21396] Mechanisms of Introspective Awareness
Abstract page for arXiv paper 2603.21396: Mechanisms of Introspective Awareness
arXiv - Machine Learning
·
3 min
·
Llms
[2603.21373] PLR: Plackett-Luce for Reordering In-Context Learning Examples
Abstract page for arXiv paper 2603.21373: PLR: Plackett-Luce for Reordering In-Context Learning Examples
arXiv - Machine Learning
·
3 min
·
Llms
[2603.21365] TIDE: Token-Informed Depth Execution for Per-Token Early Exit in LLM Inference
Abstract page for arXiv paper 2603.21365: TIDE: Token-Informed Depth Execution for Per-Token Early Exit in LLM Inference
arXiv - Machine Learning
·
4 min
·
Related Topics
Stay updated with AI News
Get the latest news, tools, and insights delivered to your inbox.
Daily or weekly digest • Unsubscribe anytime