Cover Image

Compositional Literary Primitives in Instruction-Tuned LLMs: Cross-Architectural SAE Features for Self, Style, and Affect

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Presa, Joao Paulo Cavalcante, de Oliveira, Savio Salvarino Teles
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Call2Instruct: Automated Pipeline for Generating Q&A Datasets from Call Center Recordings for LLM Fine-Tuning
by: Echeverria, Alex, et al.
Published: (2025)

How Good Are LLMs for Literary Translation, Really? Literary Translation Evaluation with Humans and LLMs
by: Zhang, Ran, et al.
Published: (2024)

Dense SAE Latents Are Features, Not Bugs
by: Sun, Xiaoqing, et al.
Published: (2025)

CrossIn: An Efficient Instruction Tuning Approach for Cross-Lingual Knowledge Alignment
by: Lin, Geyu, et al.
Published: (2024)

SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection
by: Liu, Liangxin, et al.
Published: (2024)

InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct
by: Wu, Yutong, et al.
Published: (2024)

Distilling Text Style Transfer With Self-Explanation From LLMs
by: Zhang, Chiyu, et al.
Published: (2024)

GemmAr: Enhancing LLMs Through Arabic Instruction-Tuning
by: Chouikhi, Hasna, et al.
Published: (2024)

How Reliable Are Automatic Evaluation Methods for Instruction-Tuned LLMs?
by: Doostmohammadi, Ehsan, et al.
Published: (2024)

Adapting LLMs for the Medical Domain in Portuguese: A Study on Fine-Tuning and Model Evaluation
by: Paiola, Pedro Henrique, et al.
Published: (2024)

Reasoning Primitives in Hybrid and Non-Hybrid LLMs: Do Architectural Differences Yield Advantages in State-Tracking and Recall?
by: Rawat, Shivam, et al.
Published: (2026)

xCoT: Cross-lingual Instruction Tuning for Cross-lingual Chain-of-Thought Reasoning
by: Chai, Linzheng, et al.
Published: (2024)

Building Accurate Translation-Tailored LLMs with Language Aware Instruction Tuning
by: Zan, Changtong, et al.
Published: (2024)

Measuring Embedding Sensitivity to Authorial Style in French: Comparing Literary Texts with Language Model Rewritings
by: Icard, Benjamin, et al.
Published: (2026)

LuxInstruct: A Cross-Lingual Instruction Tuning Dataset For Luxembourgish
by: Philippy, Fred, et al.
Published: (2025)

Teaching According to Talents! Instruction Tuning LLMs with Competence-Aware Curriculum Learning
by: Li, Yangning, et al.
Published: (2025)

Teaching LLMs to Plan: Logical Chain-of-Thought Instruction Tuning for Symbolic Planning
by: Verma, Pulkit, et al.
Published: (2025)

Jailbreak Instruction-Tuned LLMs via end-of-sentence MLP Re-weighting
by: Luo, Yifan, et al.
Published: (2024)

A Comparative Analysis of Instruction Fine-Tuning LLMs for Financial Text Classification
by: Fatemi, Sorouralsadat, et al.
Published: (2024)

The Right Time Matters: Data Arrangement Affects Zero-Shot Generalization in Instruction Tuning
by: He, Bingxiang, et al.
Published: (2024)

Instruction Tuning With Loss Over Instructions
by: Shi, Zhengyan, et al.
Published: (2024)

Cross-Lingual Stability and Bias in Instruction-Tuned Language Models for Humanitarian NLP
by: Nemkova, Poli, et al.
Published: (2025)

Tuning LLMs with Contrastive Alignment Instructions for Machine Translation in Unseen, Low-resource Languages
by: Mao, Zhuoyuan, et al.
Published: (2024)

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs
by: Nuti, Felipe, et al.
Published: (2025)

A Study of Large Language Models for Patient Information Extraction: Model Architecture, Fine-Tuning Strategy, and Multi-task Instruction Tuning
by: Peng, Cheng, et al.
Published: (2025)

From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning
by: Wu, Xuansheng, et al.
Published: (2023)

ClimateChat: Designing Data and Methods for Instruction Tuning LLMs to Answer Climate Change Queries
by: Chen, Zhou, et al.
Published: (2025)

Span-level Emotion-Cause-Category Triplet Extraction with Instruction Tuning LLMs and Data Augmentation
by: Li, Xiangju, et al.
Published: (2025)

Fine-Tuning Causal LLMs for Text Classification: Embedding-Based vs. Instruction-Based Approaches
by: Yousefiramandi, Amirhossein, et al.
Published: (2025)

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation
by: He, Linda, et al.
Published: (2025)

X-Instruction: Aligning Language Model in Low-resource Languages with Self-curated Cross-lingual Instructions
by: Li, Chong, et al.
Published: (2024)

A New Pipeline For Generating Instruction Dataset via RAG and Self Fine-Tuning
by: Song, Chih-Wei, et al.
Published: (2024)

Towards Automatic Continual Learning: A Self-Adaptive Framework for Continual Instruction Tuning
by: Lin, Peiyi, et al.
Published: (2025)

Rethinking Table Instruction Tuning
by: Deng, Naihao, et al.
Published: (2025)

Step-On-Feet Tuning: Scaling Self-Alignment of LLMs via Bootstrapping
by: Wang, Haoyu, et al.
Published: (2024)

Middle-Layer Representation Alignment for Cross-Lingual Transfer in Fine-Tuned LLMs
by: Liu, Danni, et al.
Published: (2025)

CroCo: Cross-Lingual Contrastive Preference Tuning on Self-Generations
by: Zhang, Mike, et al.
Published: (2026)

Instruction-Tuned, but Not More Verifiable Instruction-Following: A Cross-Task Diagnosis for LoRA Adapters
by: Zou, Junyi
Published: (2026)

Structured Thinking Matters: Improving LLMs Generalization in Causal Inference Tasks
by: Sun, Wentao, et al.
Published: (2025)

From Human Cognition to Neural Activations: Probing the Computational Primitives of Spatial Reasoning in LLMs
by: An, Jiyuan, et al.
Published: (2026)