Copertina

Polysemantic Dropout: Conformal OOD Detection for Specialized LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Gupta, Ayush, Kaur, Ramneet, Roy, Anirban, Cobb, Adam D., Chellappa, Rama, Jha, Susmit
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Scalable Bayesian Low-Rank Adaptation of Large Language Models via Stochastic Variational Subspace Inference
di: Samplawski, Colin, et al.
Pubblicazione: (2025)

Calibrating Uncertainty Quantification of Multi-Modal LLMs using Grounding
di: Padhi, Trilok, et al.
Pubblicazione: (2025)

TOGA: Temporally Grounded Open-Ended Video QA with Weak Supervision
di: Gupta, Ayush, et al.
Pubblicazione: (2025)

From Actions to Understanding: Conformal Interpretability of Temporal Concepts in LLM Agents
di: Padhi, Trilok, et al.
Pubblicazione: (2026)

Privacy Preserving In-Context-Learning Framework for Large Language Models
di: Bhusal, Bishnu, et al.
Pubblicazione: (2025)

Backpropagation-Free Metropolis-Adjusted Langevin Algorithm
di: Cobb, Adam D., et al.
Pubblicazione: (2025)

Addressing Uncertainty in LLMs to Enhance Reliability in Generative AI
di: Kaur, Ramneet, et al.
Pubblicazione: (2024)

AGENT: An Aerial Vehicle Generation and Design Tool Using Large Language Models
di: Samplawski, Colin, et al.
Pubblicazione: (2025)

Question Answering on Patient Medical Records with Private Fine-Tuned LLMs
di: Kothari, Sara, et al.
Pubblicazione: (2025)

TeleLoRA: Teleporting Model-Specific Alignment Across LLMs
di: Lin, Xiao, et al.
Pubblicazione: (2025)

Polysemanticity or Polysemy? Lexical Identity Confounds Superposition Metrics
di: Hou, Iyad Ait, et al.
Pubblicazione: (2026)

SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers
di: Pramanick, Shraman, et al.
Pubblicazione: (2024)

Optimal Abstractions for Verifying Properties of Kolmogorov-Arnold Networks (KANs)
di: Schwartz, Noah, et al.
Pubblicazione: (2026)

Closed-Loop Neural Activation Control in Vision-Language-Action Models
di: Babu, Abhijith, et al.
Pubblicazione: (2026)

Concept-based Analysis of Neural Networks via Vision-Language Models
di: Mangal, Ravi, et al.
Pubblicazione: (2024)

Farther the Shift, Sparser the Representation: Analyzing OOD Mechanisms in LLMs
di: Jin, Mingyu, et al.
Pubblicazione: (2026)

Polysemantic Experts, Monosemantic Paths: Routing as Control in MoEs
di: Ye, Charles, et al.
Pubblicazione: (2026)

Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework
di: Kopf, Laura, et al.
Pubblicazione: (2025)

Signal in the Noise: Polysemantic Interference Transfers and Predicts Cross-Model Influence
di: Gong, Bofan, et al.
Pubblicazione: (2025)

Unsupervised Layer-wise Score Aggregation for Textual OOD Detection
di: Darrin, Maxime, et al.
Pubblicazione: (2023)

Breaking Bad: Interpretability-Based Safety Audits of State-of-the-Art LLMs
di: Agarwal, Krishiv, et al.
Pubblicazione: (2026)

Spot the BlindSpots: Systematic Identification and Quantification of Fine-Grained LLM Biases in Contact Center Summaries
di: Mayilvaghanan, Kawin, et al.
Pubblicazione: (2025)

Drop Dropout on Single-Epoch Language Model Pretraining
di: Liu, Houjun, et al.
Pubblicazione: (2025)

Polysemanticity and Capacity in Neural Networks
di: Scherlis, Adam, et al.
Pubblicazione: (2022)

PIIBench: A Unified Multi-Source Benchmark Corpus for Personally Identifiable Information Detection
di: Jha, Pritesh
Pubblicazione: (2026)

Fine-Tuning Over Architectural Complexity: Broad-Coverage PII Detection on PIIBench with DeBERTa
di: Jha, Pritesh
Pubblicazione: (2026)

TECP: Token-Entropy Conformal Prediction for LLMs
di: Xu, Beining, et al.
Pubblicazione: (2025)

ViT-Linearizer: Distilling Quadratic Knowledge into Linear-Time Vision Models
di: Wei, Guoyizhe, et al.
Pubblicazione: (2025)

Hessian-Enhanced Token Attribution (HETA): Interpreting Autoregressive LLMs
di: Pramanik, Vishal, et al.
Pubblicazione: (2026)

MimicGait: A Model Agnostic approach for Occluded Gait Recognition using Correlational Knowledge Distillation
di: Gupta, Ayush, et al.
Pubblicazione: (2025)

An Empirical Study of Conformal Prediction in LLM with ASP Scaffolds for Robust Reasoning
di: Kaur, Navdeep, et al.
Pubblicazione: (2025)

Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution
di: Dineen, Jacob, et al.
Pubblicazione: (2026)

Layer-wise Regularized Dropout for Neural Language Models
di: Ni, Shiwen, et al.
Pubblicazione: (2024)

The Aloe Family Recipe for Open and Specialized Healthcare LLMs
di: Garcia-Gasulla, Dario, et al.
Pubblicazione: (2025)

Tower+: Bridging Generality and Translation Specialization in Multilingual LLMs
di: Rei, Ricardo, et al.
Pubblicazione: (2025)

Beyond Specialization: Benchmarking LLMs for Transliteration of Indian Languages
di: Azam, Gulfarogh, et al.
Pubblicazione: (2025)

General2Specialized LLMs Translation for E-commerce
di: Chen, Kaidi, et al.
Pubblicazione: (2024)

LoRA Meets Dropout under a Unified Framework
di: Wang, Sheng, et al.
Pubblicazione: (2024)

DiffRegCD: Integrated Registration and Change Detection with Diffusion Features
di: Madani, Seyedehanita, et al.
Pubblicazione: (2025)

Do Language Models Know When They're Hallucinating References?
di: Agrawal, Ayush, et al.
Pubblicazione: (2023)