Copertina

Interpreting Multi-Attribute Confounding through Numerical Attributes in Large Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Takagi, Hirohane, Minegishi, Gouki, Kizawa, Shota, Sukeda, Issey, Yanaka, Hitomi
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties
di: Minegishi, Gouki, et al.
Pubblicazione: (2025)

Towards Empirical Interpretation of Internal Circuits and Properties in Grokked Transformers on Modular Polynomials
di: Furuta, Hiroki, et al.
Pubblicazione: (2024)

RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs
di: Matsutani, Kohsei, et al.
Pubblicazione: (2025)

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words
di: Minegishi, Gouki, et al.
Pubblicazione: (2025)

Development and bilingual evaluation of Japanese medical large language model within reasonably low computational resources
di: Sukeda, Issey
Pubblicazione: (2024)

Safe Transformer: An Explicit Safety Bit For Interpretable And Controllable Alignment
di: Feng, Jingyuan, et al.
Pubblicazione: (2026)

Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence
di: Minegishi, Gouki, et al.
Pubblicazione: (2025)

Mechanism of Task-oriented Information Removal in In-context Learning
di: Cho, Hakaze, et al.
Pubblicazione: (2025)

Understanding Emergent Misalignment via Feature Superposition Geometry
di: Minegishi, Gouki, et al.
Pubblicazione: (2026)

Zipping the Thought: When and How Compressed Reasoning Data Works in LLM Post-Training
di: Matsutani, Kohsei, et al.
Pubblicazione: (2026)

Attribution Bias in Large Language Models
di: Berman, Eliza, et al.
Pubblicazione: (2026)

Advancing Large Language Model Attribution through Self-Improving
di: Huang, Lei, et al.
Pubblicazione: (2024)

Steering at the Source: Style Modulation Heads for Robust Persona Control
di: Izawa, Yoshihiro, et al.
Pubblicazione: (2026)

Analyzing Memorization in Large Language Models through the Lens of Model Attribution
di: Menta, Tarun Ram, et al.
Pubblicazione: (2025)

Adaptive Multi-Subspace Representation Steering for Attribute Alignment in Large Language Models
di: Jiang, Xinyan, et al.
Pubblicazione: (2025)

Minimum information Markov model
di: Sukeda, Issey, et al.
Pubblicazione: (2026)

Frank copula is minimum information copula under fixed Kendall's $τ$
di: Sukeda, Issey, et al.
Pubblicazione: (2024)

Relative local dependence of bivariate copulas
di: Sukeda, Issey, et al.
Pubblicazione: (2024)

On the minimum information checkerboard copulas under fixed Kendall's rank correlation
di: Sukeda, Issey, et al.
Pubblicazione: (2023)

DataDignity: Training Data Attribution for Large Language Models
di: Li, Xiaomin, et al.
Pubblicazione: (2026)

Intersectional Bias in Japanese Large Language Models from a Contextualized Perspective
di: Yanaka, Hitomi, et al.
Pubblicazione: (2025)

Multi-Attribute Constraint Satisfaction via Language Model Rewriting
di: Baheti, Ashutosh, et al.
Pubblicazione: (2024)

Source Attribution for Large Language Model-Generated Data
di: Wang, Jingtan, et al.
Pubblicazione: (2023)

Exploring the Role of Knowledge Graph-Based RAG in Japanese Medical Question Answering with Small-Scale LLMs
di: Chen, Yingjian, et al.
Pubblicazione: (2025)

Noiser: Bounded Input Perturbations for Attributing Large Language Models
di: Madani, Mohammad Reza Ghasemi, et al.
Pubblicazione: (2025)

Explaining the Reasoning of Large Language Models Using Attribution Graphs
di: Walker, Chase, et al.
Pubblicazione: (2025)

Learning to Price: Interpretable Attribute-Level Models for Dynamic Markets
di: Sethuraman, Srividhya, et al.
Pubblicazione: (2026)

Enhancing Model Interpretability with Local Attribution over Global Exploration
di: Zhu, Zhiyu, et al.
Pubblicazione: (2024)

AIM: Attributing, Interpreting, Mitigating Data Unfairness
di: Liu, Zhining, et al.
Pubblicazione: (2024)

Attributions All the Way Down? The Metagame of Interpretability
di: Baniecki, Hubert, et al.
Pubblicazione: (2026)

Attribute Based Interpretable Evaluation Metrics for Generative Models
di: Kim, Dongkyun, et al.
Pubblicazione: (2023)

Document Attribution: Examining Citation Relationships using Large Language Models
di: Rawte, Vipula, et al.
Pubblicazione: (2025)

Revisiting Large Language Model Pruning using Neuron Semantic Attribution
di: Ding, Yizhuo, et al.
Pubblicazione: (2025)

Learning Fine-Grained Grounded Citations for Attributed Large Language Models
di: Huang, Lei, et al.
Pubblicazione: (2024)

Mitigating Hidden Confounding by Progressive Confounder Imputation via Large Language Models
di: Yang, Hao, et al.
Pubblicazione: (2025)

Large Language Models as Attribution Regularizers for Efficient Model Training
di: Vukadin, Davor, et al.
Pubblicazione: (2025)

A Monosemantic Attribution Framework for Stable Interpretability in Clinical Neuroscience Transformer-Based Language Models
di: Mamalakis, Michail, et al.
Pubblicazione: (2026)

Multi-Attribute Steering of Language Models via Targeted Intervention
di: Nguyen, Duy, et al.
Pubblicazione: (2025)

Exploring the Potential of Large Language Models as Predictors in Dynamic Text-Attributed Graphs
di: Lei, Runlin, et al.
Pubblicazione: (2025)

Attributional Safety Failures in Large Language Models under Code-Mixed Perturbations
di: Banerjee, Somnath, et al.
Pubblicazione: (2025)