Image de couverture de livre

Select or Project? Evaluating Lower-dimensional Vectors for LLM Training Data Explanations

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Hinterleitner, Lukas, Schoenegger, Loris, Roth, Benjamin
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language I.2.7
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Compact Example-Based Explanations for Language Models
par: Schoenegger, Loris, et autres
Publié: (2026)

Influence-driven Curriculum Learning for Pre-training on Limited Data
par: Schoenegger, Loris, et autres
Publié: (2025)

Rubrik's Cube: Testing a New Rubric for Evaluating Explanations on the CUBE dataset
par: Galvan-Sosa, Diana, et autres
Publié: (2025)

LLM-GLOBE: A Benchmark Evaluating the Cultural Values Embedded in LLM Output
par: Karinshak, Elise, et autres
Publié: (2024)

CRISP: Persistent Concept Unlearning via Sparse Autoencoders
par: Ashuach, Tomer, et autres
Publié: (2025)

SAGE: Hierarchical LLM-Based Literary Evaluation through Ontology-Grounded Interpretive Dimensions
par: Wang, Tianyu, et autres
Publié: (2026)

Improving the OOD Performance of Closed-Source LLMs on NLI Through Strategic Data Selection
par: Stacey, Joe, et autres
Publié: (2025)

Verbosity Tradeoffs and the Impact of Scale on the Faithfulness of LLM Self-Explanations
par: Siegel, Noah Y., et autres
Publié: (2025)

Hidden Failures in Robustness: Why Supervised Uncertainty Quantification Needs Better Evaluation
par: Stacey, Joe, et autres
Publié: (2026)

Evaluating Input Feature Explanations through a Unified Diagnostic Evaluation Framework
par: Sun, Jingyi, et autres
Publié: (2024)

Learning and communication pressures in neural networks: Lessons from emergent communication
par: Galke, Lukas, et autres
Publié: (2024)

Enhancing Paraphrase Type Generation: The Impact of DPO and RLHF Evaluated with Human-Ranked Data
par: Lübbers, Christopher Lee
Publié: (2025)

LLM-Rubric: A Multidimensional, Calibrated Approach to Automated Evaluation of Natural Language Texts
par: Hashemi, Helia, et autres
Publié: (2024)

Calibrated Confidence Estimation for Tabular Question Answering
par: Voss, Lukas
Publié: (2026)

The Sufficiency-Conciseness Trade-off in LLM Self-Explanation from an Information Bottleneck Perspective
par: Zahedzadeh, Ali, et autres
Publié: (2026)

HumanLLM: Benchmarking and Improving LLM Anthropomorphism via Human Cognitive Patterns
par: Wang, Xintao, et autres
Publié: (2026)

What makes a language easy to deep-learn? Deep neural networks and humans similarly benefit from compositional structure
par: Galke, Lukas, et autres
Publié: (2023)

Tokenization and Morphology in Multilingual Language Models: A Comparative Analysis of mT5 and ByT5
par: Dang, Thao Anh, et autres
Publié: (2024)

Revisiting Word Embeddings in the LLM Era
par: Mahajan, Yash, et autres
Publié: (2024)

Evaluating the efficacy of LLM Safety Solutions : The Palit Benchmark Dataset
par: Palit, Sayon, et autres
Publié: (2025)

Interactive Text-to-SQL Generation via Editable Step-by-Step Explanations
par: Tian, Yuan, et autres
Publié: (2023)

Distinguishing Ignorance from Error in LLM Hallucinations
par: Simhi, Adi, et autres
Publié: (2024)

Decoding-Free Sampling Strategies for LLM Marginalization
par: Pohl, David, et autres
Publié: (2025)

Efficient Reasoning via Thought-Training and Thought-Free Inference
par: Wu, Canhui, et autres
Publié: (2025)

GroUSE: A Benchmark to Evaluate Evaluators in Grounded Question Answering
par: Muller, Sacha, et autres
Publié: (2024)

Masked by Consensus: Disentangling Privileged Knowledge in LLM Correctness
par: Ashuach, Tomer, et autres
Publié: (2026)

LUCID: LLM-Generated Utterances for Complex and Interesting Dialogues
par: Stacey, Joe, et autres
Publié: (2024)

Automatic Task Detection and Heterogeneous LLM Speculative Decoding
par: Ge, Danying, et autres
Publié: (2025)

Overcoming Black-box Attack Inefficiency with Hybrid and Dynamic Select Algorithms
par: Belde, Abhinay Shankar, et autres
Publié: (2025)

Policy-driven Knowledge Selection and Response Generation for Document-grounded Dialogue
par: Ma, Longxuan, et autres
Publié: (2024)

Intent Classification for Bank Chatbots through LLM Fine-Tuning
par: Lajčinová, Bibiána, et autres
Publié: (2024)

Can LLM Graph Reasoning Generalize beyond Pattern Memorization?
par: Zhang, Yizhuo, et autres
Publié: (2024)

RomanLens: The Role Of Latent Romanization In Multilinguality In LLMs
par: Saji, Alan, et autres
Publié: (2025)

Text-Based Approaches to Item Difficulty Modeling in Large-Scale Assessments: A Systematic Review
par: Peters, Sydney, et autres
Publié: (2025)

LLMBridge: An LLM Pipeline for End-to-end Referential Bridging Resolution in English
par: Levine, Lauren, et autres
Publié: (2026)

Whose Facts Win? LLM Source Preferences under Knowledge Conflicts
par: Schuster, Jakob, et autres
Publié: (2026)

SEPTQ: A Simple and Effective Post-Training Quantization Paradigm for Large Language Models
par: Liu, Han, et autres
Publié: (2026)

Augmenting Dialog with Think-Aloud Utterances for Modeling Individual Personality Traits by LLM
par: Ishikura, Seiya, et autres
Publié: (2025)

Extracting Structured Insights from Financial News: An Augmented LLM Driven Approach
par: Dolphin, Rian, et autres
Publié: (2024)

LLM-Ref: Enhancing Reference Handling in Technical Writing with Large Language Models
par: Fuad, Kazi Ahmed Asif, et autres
Publié: (2024)