Copertina

Layers at Similar Depths Generate Similar Activations Across LLM Architectures

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wolfram, Christopher, Schein, Aaron
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

Activation Scaling for Steering and Interpreting Language Models
di: Stoehr, Niklas, et al.
Pubblicazione: (2024)

Metric-Fair Prompting: Treating Similar Samples Similarly
di: Wang, Jing, et al.
Pubblicazione: (2025)

Rethinking Word Similarity: Semantic Similarity through Classification Confusion
di: Zhou, Kaitlyn, et al.
Pubblicazione: (2025)

Generative Caching for Structurally Similar Prompts and Responses
di: Chakraborty, Sarthak, et al.
Pubblicazione: (2025)

Similarity is Not All You Need: Endowing Retrieval Augmented Generation with Multi Layered Thoughts
di: Gan, Chunjing, et al.
Pubblicazione: (2024)

A Comprehensive Framework for Semantic Similarity Analysis of Human and AI-Generated Text Using Transformer Architectures and Ensemble Techniques
di: Gao, Lifu, et al.
Pubblicazione: (2025)

Bias Similarity Measurement: A Black-Box Audit of Fairness Across LLMs
di: Jeong, Hyejun, et al.
Pubblicazione: (2024)

From Similarity to Structure: Training-free LLM Context Compression with Hybrid Graph Priors
di: Zhou, Yitian, et al.
Pubblicazione: (2026)

Linguistically Conditioned Semantic Textual Similarity
di: Tu, Jingxuan, et al.
Pubblicazione: (2024)

Quantifying True Robustness: Synonymity-Weighted Similarity for Trustworthy XAI Evaluation
di: Burger, Christopher
Pubblicazione: (2025)

Reasoning before Comparison: LLM-Enhanced Semantic Similarity Metrics for Domain Specialized Text Analysis
di: Xu, Shaochen, et al.
Pubblicazione: (2024)

When Metrics Disagree: Automatic Similarity vs. LLM-as-a-Judge for Clinical Dialogue Evaluation
di: Sun, Bian, et al.
Pubblicazione: (2026)

KurdSTS: The Kurdish Semantic Textual Similarity
di: Abdullah, Abdulhady Abas, et al.
Pubblicazione: (2025)

Linear Representations of Political Perspective Emerge in Large Language Models
di: Kim, Junsol, et al.
Pubblicazione: (2025)

Consistent and Distinctive: LLM Benchmark Efficiency via Maximum Independent Set Prompt Selection on Similarity Graphs
di: Kjorvezir, Denica, et al.
Pubblicazione: (2026)

Statistical Comparative Analysis of Semantic Similarities and Model Transferability Across Datasets for Short Answer Grading
di: Bonthu, Sridevi, et al.
Pubblicazione: (2025)

Leveraging KV Similarity for Online Structured Pruning in LLMs
di: Lee, Jungmin, et al.
Pubblicazione: (2025)

Language Model Re-rankers are Fooled by Lexical Similarities
di: Hagström, Lovisa, et al.
Pubblicazione: (2025)

Estimating Text Similarity based on Semantic Concept Embeddings
di: der Brück, Tim vor, et al.
Pubblicazione: (2024)

CSS: Contrastive Semantic Similarity for Uncertainty Quantification of LLMs
di: Ao, Shuang, et al.
Pubblicazione: (2024)

Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity
di: Jiang, Jiachen, et al.
Pubblicazione: (2024)

Similar Data Points Identification with LLM: A Human-in-the-loop Strategy Using Summarization and Hidden State Insights
di: Zeng, Xianlong, et al.
Pubblicazione: (2024)

ConSCompF: Consistency-focused Similarity Comparison Framework for Generative Large Language Models
di: Karev, Alexey, et al.
Pubblicazione: (2025)

How Small Transformation Expose the Weakness of Semantic Similarity Measures
di: Nikiema, Serge Lionel, et al.
Pubblicazione: (2025)

The Same But Different: Structural Similarities and Differences in Multilingual Language Modeling
di: Zhang, Ruochen, et al.
Pubblicazione: (2024)

Automatic Design of Semantic Similarity Ensembles Using Grammatical Evolution
di: Martinez-Gil, Jorge
Pubblicazione: (2023)

Measuring the Depth of LLM Unlearning via Activation Patching
di: Lee, Jaeung, et al.
Pubblicazione: (2026)

Multi-LLM Thematic Analysis with Dual Reliability Metrics: Combining Cohen's Kappa and Semantic Similarity for Qualitative Research Validation
di: Jain, Nilesh, et al.
Pubblicazione: (2025)

DepthKV: Layer-Dependent KV Cache Pruning for Long-Context LLM Inference
di: Dehghanighobadi, Zahra, et al.
Pubblicazione: (2026)

DOCS: Quantifying Weight Similarity for Deeper Insights into Large Language Models
di: Min, Zeping, et al.
Pubblicazione: (2025)

Shared Path: Unraveling Memorization in Multilingual LLMs through Language Similarities
di: Luo, Xiaoyu, et al.
Pubblicazione: (2025)

SiReRAG: Indexing Similar and Related Information for Multihop Reasoning
di: Zhang, Nan, et al.
Pubblicazione: (2024)

Textual Similarity as a Key Metric in Machine Translation Quality Estimation
di: Sun, Kun, et al.
Pubblicazione: (2024)

SimSMoE: Solving Representational Collapse via Similarity Measure
di: Do, Giang, et al.
Pubblicazione: (2024)

PESTS: Persian_English Cross Lingual Corpus for Semantic Textual Similarity
di: Abdous, Mohammad, et al.
Pubblicazione: (2023)

Contrastive Token Learning with Similarity Decay for Repetition Suppression in Machine Translation
di: Dai, Huangyu, et al.
Pubblicazione: (2024)

Directional Attractors in LLM Reasoning: How Similarity Retrieval Steers Iterative Summarization Based Reasoning
di: Tekin, Cagatay, et al.
Pubblicazione: (2025)

SIMBA UQ: Similarity-Based Aggregation for Uncertainty Quantification in Large Language Models
di: Bhattacharjya, Debarun, et al.
Pubblicazione: (2025)

Chopping Trees: Semantic Similarity Based Dynamic Pruning for Tree-of-Thought Reasoning
di: Kim, Joongho, et al.
Pubblicazione: (2025)

Magnitude Matters: a Superior Class of Similarity Metrics for Holistic Semantic Understanding
di: Parupudi, V. S. Raghu
Pubblicazione: (2025)