Copertina

Analyzing the Inner Workings of Transformers in Compositional Generalization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kumon, Ryoma, Yanaka, Hitomi
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Fine-Grained Analysis of Shared Syntactic Mechanisms in Language Models
di: Kumon, Ryoma, et al.
Pubblicazione: (2026)

Evaluating Structural Generalization in Neural Machine Translation
di: Kumon, Ryoma, et al.
Pubblicazione: (2024)

Bias Mitigation or Cultural Commonsense? Evaluating LLMs with a Japanese Dataset
di: Yamamoto, Taisei, et al.
Pubblicazione: (2025)

Neuron-Level Analysis of Cultural Understanding in Large Language Models
di: Yamamoto, Taisei, et al.
Pubblicazione: (2025)

JBBQ: Japanese Bias Benchmark for Analyzing Social Biases in Large Language Models
di: Yanaka, Hitomi, et al.
Pubblicazione: (2024)

Enhancing Rating Prediction with Off-the-Shelf LLMs Using In-Context User Reviews
di: Ryu, Koki, et al.
Pubblicazione: (2025)

NeuronMoE: Neuron-Guided Mixture-of-Experts for Efficient Multilingual LLM Extension
di: Li, Rongzhi, et al.
Pubblicazione: (2026)

What Do Vision-Language Models Encode for Personalized Image Aesthetics Assessment?
di: Ryu, Koki, et al.
Pubblicazione: (2026)

Investigating Training and Generalization in Faithful Self-Explanations of Large Language Models
di: Doi, Tomoki, et al.
Pubblicazione: (2025)

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

Can Large Language Models Robustly Perform Natural Language Inference for Japanese Comparatives?
di: Mikami, Yosuke, et al.
Pubblicazione: (2025)

LLMs Struggle with NLI for Perfect Aspect: A Cross-Linguistic Study in Chinese and Japanese
di: Lu, Jie, et al.
Pubblicazione: (2025)

Implementing a Logical Inference System for Japanese Comparatives
di: Mikami, Yosuke, et al.
Pubblicazione: (2025)

Comprehensive Evaluation of Large Language Models for Topic Modeling
di: Doi, Tomoki, et al.
Pubblicazione: (2024)

Exploring Intra and Inter-language Consistency in Embeddings with ICA
di: Li, Rongzhi, et al.
Pubblicazione: (2024)

Derivational Probing: Unveiling the Layer-wise Derivation of Syntactic Structures in Neural Language Models
di: Someya, Taiga, et al.
Pubblicazione: (2025)

Towards Automated Lexicography: Generating and Evaluating Definitions for Learner's Dictionaries
di: Ide, Yusuke, et al.
Pubblicazione: (2026)

On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons
di: Kojima, Takeshi, et al.
Pubblicazione: (2024)

Do Large Vision-Language Models Distinguish between the Actual and Apparent Features of Illusions?
di: Shinozaki, Taiga, et al.
Pubblicazione: (2025)

A Primer on the Inner Workings of Transformer-based Language Models
di: Ferrando, Javier, et al.
Pubblicazione: (2024)

Bridging Perception and Language: A Systematic Benchmark for LVLMs' Understanding of Amodal Completion Reports
di: Watahiki, Amane, et al.
Pubblicazione: (2025)

Sakura at BEA 2026 Shared Task 1: What Makes Vocabulary Difficult?
di: Nohejl, Adam, et al.
Pubblicazione: (2026)

J-CHAT: Japanese Large-scale Spoken Dialogue Corpus for Spoken Dialogue Language Modeling
di: Nakata, Wataru, et al.
Pubblicazione: (2024)

Developing a Guideline for the Labovian-Structural Analysis of Oral Narratives in Japanese
di: Watahiki, Amane, et al.
Pubblicazione: (2026)

Analyzing And Editing Inner Mechanisms Of Backdoored Language Models
di: Lamparth, Max, et al.
Pubblicazione: (2023)

Automatic Prompt Generation via Adaptive Selection of Prompting Techniques
di: Ikenoue, Yohei, et al.
Pubblicazione: (2025)

Even GPT-5.2 Can't Count to Five: The Case for Zero-Error Horizons in Trustworthy LLMs
di: Sato, Ryoma
Pubblicazione: (2026)

The Impact of Depth on Compositional Generalization in Transformer Language Models
di: Petty, Jackson, et al.
Pubblicazione: (2023)

Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking
di: Chen, Yilong, et al.
Pubblicazione: (2025)

Inner-Probe: Discovering Copyright-related Data Generation in LLM Architecture
di: Ma, Qichao, et al.
Pubblicazione: (2024)

Multilingual KokoroChat: A Multi-LLM Ensemble Translation Method for Creating a Multilingual Counseling Dialogue Dataset
di: Suzuki, Ryoma, et al.
Pubblicazione: (2026)

Hierarchical Narrative Analysis: Unraveling Perceptions of Generative AI
di: Matsuoka, Riona, et al.
Pubblicazione: (2024)

LM Transparency Tool: Interactive Tool for Analyzing Transformer Language Models
di: Tufanov, Igor, et al.
Pubblicazione: (2024)

Analyzing Feed-Forward Blocks in Transformers through the Lens of Attention Maps
di: Kobayashi, Goro, et al.
Pubblicazione: (2023)

Shallow Synthesis of Knowledge in GPT-Generated Texts: A Case Study in Automatic Related Work Composition
di: Martin-Boyle, Anna, et al.
Pubblicazione: (2024)

Mind the Gap: Analyzing Lacunae with Transformer-Based Transcription
di: Borkar, Jaydeep, et al.
Pubblicazione: (2024)

User-Side Realization
di: Sato, Ryoma
Pubblicazione: (2024)

Annotating Compositionality Scores for Irish Noun Compounds is Hard Work
di: Walsh, Abigail, et al.
Pubblicazione: (2025)

Complexity Control Facilitates Reasoning-Based Compositional Generalization in Transformers
di: Zhang, Zhongwang, et al.
Pubblicazione: (2025)

Revisiting Observation Reduction for Web Agents: Comprehensive Evaluation with a Lightweight Framework
di: Enomoto, Masafumi, et al.
Pubblicazione: (2026)