:: Library Catalog

Copertina

Salvato in:

Dettagli Bibliografici
Autori principali:	Mofael, Abdullah Al, Kuhn, Lisa M., Alkadi, Ghassan, Yang, Kuo-Pao
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	https://arxiv.org/abs/2603.12423
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Mechanistic Interpretability of GPT-2: Lexical and Contextual Layers in Sentiment Analysis
di: Hatua, Amartya
Pubblicazione: (2025)

FourierKAN outperforms MLP on Text Classification Head Fine-tuning
di: Imran, Abdullah Al, et al.
Pubblicazione: (2024)

Positional Cognitive Specialization: Where Do LLMs Learn To Comprehend and Speak Your Language?
di: Salim, Luis Frentzen, et al.
Pubblicazione: (2026)

Large Language Model Pruning
di: Huang, Hanjuan, et al.
Pubblicazione: (2024)

ChatGPT Evaluation on Sentence Level Relations: A Focus on Temporal, Causal, and Discourse Relations
di: Chan, Chunkit, et al.
Pubblicazione: (2023)

The Mechanics of Conceptual Interpretation in GPT Models: Interpretative Insights
di: Aljaafari, Nura, et al.
Pubblicazione: (2024)

Is ChatGPT the Future of Causal Text Mining? A Comprehensive Evaluation and Analysis
di: Takayanagi, Takehiro, et al.
Pubblicazione: (2024)

Interpreting Transformers Through Attention Head Intervention
di: Kadem, Mason, et al.
Pubblicazione: (2026)

Causal Interventions on Causal Paths: Mapping GPT-2's Reasoning From Syntax to Semantics
di: Lee, Isabelle, et al.
Pubblicazione: (2024)

Single and Multi-Hop Question-Answering Datasets for Reticular Chemistry with GPT-4-Turbo
di: Rampal, Nakul, et al.
Pubblicazione: (2024)

CausalDetox: Causal Head Selection and Intervention for Language Model Detoxification
di: Wang, Yian, et al.
Pubblicazione: (2026)

Generating Hard-Negative Out-of-Scope Data with ChatGPT for Intent Classification
di: Li, Zhijian, et al.
Pubblicazione: (2024)

BengaliFig: A Low-Resource Challenge for Figurative and Culturally Grounded Reasoning in Bengali
di: Sefat, Abdullah Al
Pubblicazione: (2025)

Reversed Attention: On The Gradient Descent Of Attention Layers In GPT
di: Katz, Shahar, et al.
Pubblicazione: (2024)

Evaluating the Predictive Capacity of ChatGPT for Academic Peer Review Outcomes Across Multiple Platforms
di: Thelwall, Mike, et al.
Pubblicazione: (2024)

Interpretability at Scale: Identifying Causal Mechanisms in Alpaca
di: Wu, Zhengxuan, et al.
Pubblicazione: (2023)

InfraGPT Smart Infrastructure: An End-to-End VLM-Based Framework for Detecting and Managing Urban Defects
di: Mohamed, Ibrahim Sheikh, et al.
Pubblicazione: (2025)

SpeLLM: Character-Level Multi-Head Decoding
di: Ben-Artzy, Amit, et al.
Pubblicazione: (2025)

Debiasing CLIP: Interpreting and Correcting Bias in Attention Heads
di: Yeo, Wei Jie, et al.
Pubblicazione: (2025)

You can remove GPT2's LayerNorm by fine-tuning
di: Heimersheim, Stefan
Pubblicazione: (2024)

Interpretable Next-token Prediction via the Generalized Induction Head
di: Kim, Eunji, et al.
Pubblicazione: (2024)

Feature Extraction and Analysis for GPT-Generated Text
di: Selvioğlu, A., et al.
Pubblicazione: (2025)

The Qiyas Benchmark: Measuring ChatGPT Mathematical and Language Understanding in Arabic
di: Al-Khalifa, Shahad, et al.
Pubblicazione: (2024)

Freeze Deep, Train Shallow: Interpretable Layer Allocation for Continued Pre-Training
di: Wu, Yu-Hang, et al.
Pubblicazione: (2026)

ChatGPT4PCG Competition: Character-like Level Generation for Science Birds
di: Taveekitworachai, Pittawat, et al.
Pubblicazione: (2023)

Geometric Interpretation of Layer Normalization and a Comparative Analysis with RMSNorm
di: Gupta, Akshat, et al.
Pubblicazione: (2024)

EmoBang: Detecting Emotion From Bengali Texts
di: Maruf, Abdullah Al, et al.
Pubblicazione: (2025)

A comparison of Human, GPT-3.5, and GPT-4 Performance in a University-Level Coding Course
di: Yeadon, Will, et al.
Pubblicazione: (2024)

ExaGPT: Example-Based Machine-Generated Text Detection for Human Interpretability
di: Koike, Ryuto, et al.
Pubblicazione: (2025)

Evaluating Subword Tokenization Techniques for Bengali: A Benchmark Study with BengaliBPE
di: Patwary, Firoj Ahmmed, et al.
Pubblicazione: (2025)

From Interpretability to Performance: Optimizing Retrieval Heads for Long-Context Language Models
di: Ma, Youmi, et al.
Pubblicazione: (2026)

Preference Heads in Large Language Models: A Mechanistic Framework for Interpretable Personalization
di: Zhang, Weixu, et al.
Pubblicazione: (2026)

TermGPT: Multi-Level Contrastive Fine-Tuning for Terminology Adaptation in Legal and Financial Domain
di: Sun, Yidan, et al.
Pubblicazione: (2025)

Thunder-NUBench: A Benchmark for LLMs' Sentence-Level Negation Understanding
di: So, Yeonkyoung, et al.
Pubblicazione: (2025)

ReBeCA: Unveiling Interpretable Behavior Hierarchy behind the Iterative Self-Reflection of Language Models with Causal Analysis
di: Yan, Tianqiang, et al.
Pubblicazione: (2026)

Benchmarking Commercial ASR Systems on Code-Switching Speech: Arabic, Persian, and German
di: Abdoli, Sajjad, et al.
Pubblicazione: (2026)

SkipGPT: Dynamic Layer Pruning Reinvented with Token Awareness and Module Decoupling
di: Zhao, Anhao, et al.
Pubblicazione: (2025)

Mechanistic Interpretability of GPT-like Models on Summarization Tasks
di: Mishra, Anurag
Pubblicazione: (2025)

Redefining Experts: Interpretable Decomposition of Language Models for Toxicity Mitigation
di: Shaik, Zuhair Hasan, et al.
Pubblicazione: (2025)

Mechanism and Emergence of Stacked Attention Heads in Multi-Layer Transformers
di: Musat, Tiberiu
Pubblicazione: (2024)