No article text was recorded for this version.
optimal layer selection (intermediate layer utility)
Version 1 of 166 papers78 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering
- Blog: Unsupervised Bitext Mining and Translation via Self-trained Contextual Embeddings
- Blog: Unsupervised Lexical Substitution with Decontextualised Embeddings
- Blog: Unsupervised Multilingual Sentence Embeddings for Parallel Corpus Mining
- Blog: Comparing Static and Contextual Distributional Semantic Models on Intrinsic Tasks: An Evaluation on Mandarin Chinese Datasets
- Blog: Multilingual Sentence Transformer as A Multilingual Word Aligner
- Blog: SentSim: Crosslingual Semantic Evaluation of Machine Translation
- Blog: On the Language Neutrality of Pre-trained Multilingual Representations
- Blog: Does Representation Matter? Exploring Intermediate Layers in Large Language Models
- Blog: A Systematic Comparison of Contextualized Word Embeddings for Lexical Semantic Change
- Blog: DeTriever: Decoder-representation-based Retriever for Improving NL2SQL In-Context Learning
- Blog: Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs
- Blog: Hidden State Variability of Pretrained Language Models Can Guide Computation Reduction for Transfer Learning
- Blog: Clustering Properties of Self-Supervised Learning
- Blog: Think Then Embed: Generative Context Improves Multimodal Embedding
- Blog: A Deep Dive into Multi-Head Attention and Multi-Aspect Embedding
- Blog: LLM-based Embeddings: Attention Values Encode Sentence Semantics Better Than Hidden States
- Blog: BERT-kNN: Adding a kNN Search Component to Pretrained Language Models for Better QA
- Blog: TransformerRanker: A Tool for Efficiently Finding the Best-Suited Language Models for Downstream Classification Tasks
- Blog: Cross Modal Distillation for Supervision Transfer
- Blog: RepEval: Effective Text Evaluation with LLM Representation
- Blog: Fill the GAP: Exploiting BERT for Pronoun Resolution
- Blog: FreeRet: MLLMs as Training-Free Retrievers
- Blog: One Word, Two Sides: Traces of Stance in Contextualized Word Representations
- Blog: Think Then Embed: Generative Context Improves Multimodal Embedding
- Blog: SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddings
- Blog: Meta-Task Prompting Elicits Embeddings from Large Language Models
- Blog: Semantic Re-tuning with Contrastive Tension
- Blog: A Cross-Lingual Sentence Similarity Calculation Method With Multifeature Fusion
- Blog: Self-supervised Cross-modal Pretraining for Speech Emotion Recognition and Sentiment Analysis
- Blog: Un mot, deux facettes : traces des opinions dans les représentations contextualisées des mots
- Blog: Uncovering the Latent Potential of Deep Intermediate Representations
- Blog: Probing Critical Learning Dynamics of PLMs for Hate Speech Detection
- Blog: Optimizing Multi-Hop Document Retrieval Through Intermediate Representations
- Blog: Language Representation Projection: Can We Transfer Factual Knowledge across Languages in Multilingual Language Models?
- Blog: DETAIL: Task DEmonsTration Attribution for Interpretable In-context Learning
- Blog: Layer by Layer: Uncovering Hidden Representations in Language Models
- Blog: Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs
- Blog: CodeBERTScore: Evaluating Code Generation with Pretrained Models of Code
- Blog: Latte: Transfering LLMs' Latent-level Knowledge for Few-shot Tabular Learning
- Blog: Combining Tradition with Modernness: Exploring Event Representations in Vision-and-Language Models for Visual Goal-Step Inference
- Blog: SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens
- Blog: Efficient Supervised Training of Audio Transformers for Music Representation Learning
- Blog: Quantifying the Contextualization of Word Representations with Semantic Class Probing
- Blog: BERT-kNN: Adding a kNN Search Component to Pretrained Language Models for Better QA
- Blog: Combining Static Word Embeddings and Contextual Representations for Bilingual Lexicon Induction
- Blog: Boosting Explainability through Selective Rationalization in Pre-trained Language Models
- Blog: Evaluating Contextual Embeddings and their Extraction Layers for Depression Assessment
- Blog: Exploring the Relationship between Alignment and Cross-lingual Transfer in Multilingual Transformers
- Blog: PLD+: Accelerating LLM Inference by Leveraging Language Model Artifacts
- Blog: The geometry of hidden representations of large transformer models
- Blog: The Time-Embedding Travelers at WiC-ITA
- Blog: TC-DWA: Text Clustering with Dual Word-Level Augmentation
- Blog: Probing Multimodal Large Language Models for Global and Local Semantic Representations
- Blog: (Chat)GPT v BERT Dawn of Justice for Semantic Change Detection
- Blog: BERTScore: Evaluating Text Generation with BERT
- Blog: CodeBERTScore: Evaluating Code Generation with Pretrained Models of Code
- Blog: Pooling And Attention: What Are Effective Designs For LLM-Based Embedding Models?
- Blog: A Joint Neural Model for Information Extraction with Global Features
- Blog: CopyNext: Explicit Span Copying and Alignment in Sequence to Sequence Models
Showing 60 of 66 papers.
History & citation
Current · Permanent link
- This direction split from Semantic Embeddings from Intermediate Transformer Layers (64% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_optimal_layer_selection_intermediate_lay_c3ab5c96,
title = {optimal layer selection (intermediate layer utility)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/optimal-layer-selection-intermediate-layer-utility/rdr_c3ab5c9629114eaf9ead651030ee568f},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_optimal_layer_selection_intermediate_lay_c3ab5c96_v1,
title = {optimal layer selection (intermediate layer utility)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/optimal-layer-selection-intermediate-layer-utility/rdr_c3ab5c9629114eaf9ead651030ee568f/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}