Copertina

Mean-Pooled Cosine Similarity is Not Length-Invariant: Theory and Cross-Domain Evidence for a Length-Invariant Alternative

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Mitra, Sibayan, Kumar, Dhruv
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Machine Learning I.2.7; I.2.6
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Bayesian Attention Mechanism: A Probabilistic Framework for Positional Encoding and Context Length Extrapolation
di: Bianchessi, Arthur S., et al.
Pubblicazione: (2025)

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning
di: Mi, Zhendong, et al.
Pubblicazione: (2025)

HyDRA: Hybrid Dynamic Routing Architecture for Heterogeneous LLM Pools
di: Garg, Aashna, et al.
Pubblicazione: (2026)

Entropy-Based Measurement of Value Drift and Alignment Work in Large Language Models
di: Fadli, Samih
Pubblicazione: (2025)

TRiMS: Real-Time Tracking of Minimal Sufficient Length for Efficient Reasoning via RL
di: Bian, Tingcheng, et al.
Pubblicazione: (2026)

Discovering Transformer Circuits via a Hybrid Attribution and Pruning Framework
di: Gu, Hao, et al.
Pubblicazione: (2025)

Thread Detection and Response Generation using Transformers with Prompt Optimisation
di: T, Kevin Joshua, et al.
Pubblicazione: (2024)

Overclocking LLM Reasoning: Monitoring and Controlling Thinking Path Lengths in LLMs
di: Eisenstadt, Roy, et al.
Pubblicazione: (2025)

Quantization-Robust LLM Unlearning via Low-Rank Adaptation
di: Abitante, João Vitor Boer, et al.
Pubblicazione: (2026)

Annotation Entropy Predicts Per-Example Learning Dynamics in LoRA Fine-Tuning
di: Steele, Brady
Pubblicazione: (2026)

OCRR: A Benchmark for Online Correction Recovery under Distribution Shift
di: Grassi, Adrian
Pubblicazione: (2026)

Self-Pruned Key-Value Attention: Learning When to Write by Predicting Future Utility
di: Szilvasy, Gergely, et al.
Pubblicazione: (2026)

Ouroboros: Dynamic Weight Generation for Recursive Transformers via Input-Conditioned LoRA Modulation
di: Jaber, Jaber, et al.
Pubblicazione: (2026)

Future Token Prediction -- Causal Language Modelling with Per-Token Semantic State Vector for Multi-Token Prediction
di: Walker, Nicholas
Pubblicazione: (2024)

Neural Activation Patterns Across Language Model Architectures: A Comprehensive Analysis of Cognitive Task Performance
di: Naser-Moghadasi, Mahdi, et al.
Pubblicazione: (2026)

Representation-Aware Unlearning via Activation Signatures: From Suppression to Entity-Signature Erasure
di: Mahmood, Syed Naveed, et al.
Pubblicazione: (2026)

When Models Can't Follow: Testing Instruction Adherence Across 256 LLMs
di: Young, Richard J., et al.
Pubblicazione: (2025)

Continuous-Depth Transformers with Learned Control Dynamics
di: Jemley, Peter
Pubblicazione: (2026)

PersonalLLM: Tailoring LLMs to Individual Preferences
di: Zollo, Thomas P., et al.
Pubblicazione: (2024)

TIME: Temporally Intelligent Meta-reasoning Engine for Context-Triggered Explicit Reasoning
di: Das, Susmit
Pubblicazione: (2026)

Rethinking Addressing in Language Models via Contexualized Equivariant Positional Encoding
di: Zhu, Jiajun, et al.
Pubblicazione: (2025)

Sarcasm Detection in a Less-Resourced Language
di: Đoković, Lazar, et al.
Pubblicazione: (2024)

The Data Efficiency Frontier of Financial Foundation Models: Scaling Laws from Continued Pretraining
di: Ponnock, Jesse
Pubblicazione: (2025)

Combining Language and Topic Models for Hierarchical Text Classification
di: Toit, Jaco du, et al.
Pubblicazione: (2025)

Pre-trained Models Perform the Best When Token Distributions Follow Zipf's Law
di: He, Yanjin, et al.
Pubblicazione: (2025)

Are LLM Uncertainty and Correctness Encoded by the Same Features? A Functional Dissociation via Sparse Autoencoders
di: Patel, Het, et al.
Pubblicazione: (2026)

Memory Bank Compression for Continual Adaptation of Large Language Models
di: Katraouras, Thomas, et al.
Pubblicazione: (2026)

Kronecker Embeddings: Byte-Level Structured Token Representations for Parameter-Efficient Language Models
di: Shravan, Rohan
Pubblicazione: (2026)

Your Pretrained Model Tells the Difficulty Itself: A Self-Adaptive Curriculum Learning Paradigm for Natural Language Understanding
di: Feng, Qi, et al.
Pubblicazione: (2025)

Language Models Are Implicitly Continuous
di: Marro, Samuele, et al.
Pubblicazione: (2025)

LLM Vocabulary Compression for Low-Compute Environments
di: Vennam, Sreeram, et al.
Pubblicazione: (2024)

How Language Models Process Out-of-Distribution Inputs: A Two-Pathway Framework
di: Saghir, Hamidreza
Pubblicazione: (2026)

Stratified Hazard Sampling: Minimal-Variance Event Scheduling for CTMC/DTMC Discrete Diffusion and Flow Models
di: Jang, Seunghwan, et al.
Pubblicazione: (2026)

The Right Answer, the Wrong Direction: Why Transformers Fail at Counting and How to Fix It
di: Garcia, Gabriel
Pubblicazione: (2026)

Towards Resource-Efficient Multimodal Intelligence: Learned Routing among Specialized Expert Models
di: Saini, Mayank, et al.
Pubblicazione: (2025)

Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy
di: Lan, Guangchen, et al.
Pubblicazione: (2026)

SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference
di: Chauhan, Anay, et al.
Pubblicazione: (2026)

Domain-Specific Pretraining of Language Models: A Comparative Study in the Medical Field
di: Kerner, Tobias
Pubblicazione: (2024)

Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive Representations
di: Kumar, Sachin
Pubblicazione: (2026)

Mitigating Cross-Lingual Cultural Inconsistencies in LLMs via Consensus-Driven Preference Optimisation
di: Resck, Lucas, et al.
Pubblicazione: (2026)