Image de couverture de livre

Prediction is not Explanation: Revisiting the Explanatory Capacity of Mapping Embeddings

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Herasimchyk, Hanna, Abdelhalim, Alhassan, Laue, Sören, Regneri, Michaela
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Detecting Conceptual Abstraction in LLMs
par: Regneri, Michaela, et autres
Publié: (2024)

LLMs Explain't: A Post-Mortem on Semantic Interpretability in Transformer Models
par: Abdelhalim, Alhassan, et autres
Publié: (2026)

Automating Violence Detection and Categorization from Ancient Texts
par: Abdelhalim, Alhassan, et autres
Publié: (2025)

A Structural Theory of Position Bias in Transformers
par: Herasimchyk, Hanna, et autres
Publié: (2026)

Explanatory Summarization with Discourse-Driven Planning
par: Liu, Dongqi, et autres
Publié: (2025)

Evaluating Explanations: An Explanatory Virtues Framework for Mechanistic Interpretability -- The Strange Science Part I.ii
par: Ayonrinde, Kola, et autres
Publié: (2025)

Probing to Refine: Reinforcement Distillation of LLMs via Explanatory Inversion
par: Tan, Zhen, et autres
Publié: (2026)

Revisiting the Capacity Gap in Chain-of-Thought Distillation from a Practical Perspective
par: Kajitsuka, Tokio, et autres
Publié: (2026)

Polysemy of Synthetic Neurons Towards a New Type of Explanatory Categorical Vector Spaces
par: Pichat, Michael, et autres
Publié: (2025)

What Do Large Language Models Know? Tacit Knowledge as a Potential Causal-Explanatory Structure
par: Budding, Céline
Publié: (2025)

Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning
par: Chen, Yanda, et autres
Publié: (2024)

DSTI at LLMs4OL 2024 Task A: Intrinsic versus extrinsic knowledge for type classification
par: Akl, Hanna Abi
Publié: (2024)

Joint Design of Protein Surface and Structure Using a Diffusion Bridge Model
par: Li, Guanlue, et autres
Publié: (2025)

A Self-matching Training Method with Annotation Embedding Models for Ontology Subsumption Prediction
par: Shiraishi, Yukihiro, et autres
Publié: (2024)

Exploring Explanations Improves the Robustness of In-Context Learning
par: Honda, Ukyo, et autres
Publié: (2025)

How Causal Abstraction Underpins Computational Explanation
par: Geiger, Atticus, et autres
Publié: (2025)

Estimation of Concept Explanations Should be Uncertainty Aware
par: Piratla, Vihari, et autres
Publié: (2023)

CoSy: Evaluating Textual Explanations of Neurons
par: Kopf, Laura, et autres
Publié: (2024)

Revisiting the Superficial Alignment Hypothesis
par: Raghavendra, Mohit, et autres
Publié: (2024)

Mapping Transformer Leveraged Embeddings for Cross-Lingual Document Representation
par: Tashu, Tsegaye Misikir, et autres
Publié: (2024)

Contrastive Token-level Explanations for Graph-based Rumour Detection
par: Chin, Daniel Wai Kit, et autres
Publié: (2025)

Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations
par: Matton, Katie, et autres
Publié: (2025)

FaithLM: Towards Faithful Explanations for Large Language Models
par: Chuang, Yu-Neng, et autres
Publié: (2024)

CELL your Model: Contrastive Explanations for Large Language Models
par: Luss, Ronny, et autres
Publié: (2024)

Towards the Law of Capacity Gap in Distilling Language Models
par: Zhang, Chen, et autres
Publié: (2023)

Empirical Capacity Model for Self-Attention Neural Networks
par: Härmä, Aki, et autres
Publié: (2024)

Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets
par: Yukhymenko, Hanna, et autres
Publié: (2026)

Revisiting the Shape Convention of Transformer Language Models
par: Liao, Feng-Ting, et autres
Publié: (2026)

Neutral Residues: Revisiting Adapters for Model Extension
par: Talla, Franck Signe, et autres
Publié: (2024)

Exploring the Hidden Capacity of LLMs for One-Step Text Generation
par: Mezentsev, Gleb, et autres
Publié: (2025)

Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts
par: He, Shwai, et autres
Publié: (2025)

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency
par: Hu, Jerry Yao-Chieh, et autres
Publié: (2024)

ctELM: Decoding and Manipulating Embeddings of Clinical Trials with Embedding Language Models
par: Ondov, Brian, et autres
Publié: (2026)

Embedding Trust: Semantic Isotropy Predicts Nonfactuality in Long-Form Text Generation
par: Bhardwaj, Dhrupad, et autres
Publié: (2025)

Rule2Text: Natural Language Explanation of Logical Rules in Knowledge Graphs
par: Shirvani-Mahdavi, Nasim, et autres
Publié: (2025)

LLMExplainer: Large Language Model based Bayesian Inference for Graph Explanation Generation
par: Zhang, Jiaxing, et autres
Publié: (2024)

Show Me How It's Done: The Role of Explanations in Fine-Tuning Language Models
par: Ballout, Mohamad, et autres
Publié: (2024)

Revisiting Uncertainty Estimation and Calibration of Large Language Models
par: Tao, Linwei, et autres
Publié: (2025)

Revisiting Entropy in Reinforcement Learning for Large Reasoning Models
par: Jin, Renren, et autres
Publié: (2025)

Revisiting Multilingual Data Mixtures in Language Model Pretraining
par: Foroutan, Negar, et autres
Publié: (2025)