Image de couverture de livre

Language Model Maps for Prompt-Response Distributions via Log-Likelihood Vectors

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Takase, Yusuke, Oyama, Momose, Shimodaira, Hidetoshi
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Mapping 1,000+ Language Models via the Log-Likelihood Vector
par: Oyama, Momose, et autres
Publié: (2025)

Likelihood Variance as Text Importance for Resampling Texts to Map Language Models
par: Oyama, Momose, et autres
Publié: (2025)

Domain Mixture Design via Log-Likelihood Differences for Aligning Language Models with a Target Model
par: Kishino, Ryo, et autres
Publié: (2026)

Establishing a Scale for Kullback-Leibler Divergence in Language Models Across Various Settings
par: Kishino, Ryo, et autres
Publié: (2025)

Revisiting Cosine Similarity via Normalized ICA-transformed Embeddings
par: Yamagiwa, Hiroaki, et autres
Publié: (2024)

Understanding Higher-Order Correlations Among Semantic Components in Embeddings
par: Oyama, Momose, et autres
Publié: (2024)

Measuring Affinity between Attention-Head Weight Subspaces via the Projection Kernel
par: Yamagiwa, Hiroaki, et autres
Publié: (2026)

Axis Tour: Word Tour Determines the Order of Axes in ICA-transformed Embeddings
par: Yamagiwa, Hiroaki, et autres
Publié: (2024)

DeLTa: A Decoding Strategy based on Logit Trajectory Prediction Improves Factuality and Reasoning Ability
par: He, Yunzhen, et autres
Publié: (2025)

Knowledge Sanitization of Large Language Models
par: Ishibashi, Yoichi, et autres
Publié: (2023)

Predicting drug-gene relations via analogy tasks with word embeddings
par: Yamagiwa, Hiroaki, et autres
Publié: (2024)

Shimo Lab at "Discharge Me!": Discharge Summarization by Prompt-Driven Concatenation of Electronic Health Record Sections
par: He, Yunzhen, et autres
Publié: (2024)

3D Rotation and Translation for Hyperbolic Knowledge Graph Embedding
par: Zhu, Yihua, et autres
Publié: (2023)

Norm of Mean Contextualized Embeddings Determines their Variance
par: Yamagiwa, Hiroaki, et autres
Publié: (2024)

Block-Diagonal Orthogonal Relation and Matrix Entity for Knowledge Graph Embedding
par: Zhu, Yihua, et autres
Publié: (2024)

Beyond Chains: Bridging Large Language Models and Knowledge Bases in Complex Question Answering
par: Zhu, Yihua, et autres
Publié: (2025)

Quantifying Lexical Semantic Shift via Unbalanced Optimal Transport
par: Kishino, Ryo, et autres
Publié: (2024)

Zipfian Whitening
par: Yokoi, Sho, et autres
Publié: (2024)

Self-Translate-Train: Enhancing Cross-Lingual Transfer of Large Language Models via Inherent Capability
par: Ri, Ryokan, et autres
Publié: (2024)

Natural Fingerprints of Large Language Models
par: Suzuki, Teppei, et autres
Publié: (2025)

ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods
par: Xie, Roy, et autres
Publié: (2024)

Interpretable Online Log Analysis Using Large Language Models with Prompt Strategies
par: Liu, Yilun, et autres
Publié: (2023)

Memorization, Emergence, and Explaining Reversal Failures: A Controlled Study of Relational Semantics in LLMs
par: Zhu, Yihua, et autres
Publié: (2026)

Reasoning Depth and Environment Complexity: A Controlled Study of RLVR Data Allocation across Logical Reasoning Tasks
par: Zhu, Yihua, et autres
Publié: (2026)

Large Vocabulary Size Improves Large Language Models
par: Takase, Sho, et autres
Publié: (2024)

Position: Vector Prompt Interfaces Should Be Exposed to Enable Customization of Large Language Models
par: Yang, Liangwei, et autres
Publié: (2026)

Log-Likelihood, Simpson's Paradox, and the Detection of Machine-Generated Text
par: Kempton, Tom, et autres
Publié: (2026)

Scaling Laws for Upcycling Mixture-of-Experts Language Models
par: Liew, Seng Pei, et autres
Publié: (2025)

Spike No More: Stabilizing the Pre-training of Large Language Models
par: Takase, Sho, et autres
Publié: (2023)

Unleashing the Potentials of Likelihood Composition for Multi-modal Language Models
par: Zhao, Shitian, et autres
Publié: (2024)

Distribution Prompting: Understanding the Expressivity of Language Models Through the Next-Token Distributions They Can Produce
par: Wang, Haojin, et autres
Publié: (2025)

Mapping from Meaning: Addressing the Miscalibration of Prompt-Sensitive Language Models
par: Cox, Kyle, et autres
Publié: (2025)

Demystifying Prompts in Language Models via Perplexity Estimation
par: Gonen, Hila, et autres
Publié: (2022)

Toward LLMs Beyond English-Centric Development
par: Takase, Sho, et autres
Publié: (2026)

Aligning Language Models Using Follow-up Likelihood as Reward Signal
par: Zhang, Chen, et autres
Publié: (2024)

LogEval: A Comprehensive Benchmark Suite for Large Language Models In Log Analysis
par: Cui, Tianyu, et autres
Publié: (2024)

Understanding the Relationship between Prompts and Response Uncertainty in Large Language Models
par: Zhang, Ze Yu, et autres
Publié: (2024)

From Prompt Risk to Response Risk: Paired Analysis of Safety Behavior of Large Language Model
par: Hu, Mengya, et autres
Publié: (2026)

An Active Inference Strategy for Prompting Reliable Responses from Large Language Models in Medical Practice
par: Shusterman, Roma, et autres
Publié: (2024)

Task Prompt Vectors: Effective Initialization through Multi-Task Soft-Prompt Transfer
par: Belanec, Robert, et autres
Publié: (2024)