Cover Image

How Instruction-Tuning Imparts Length Control: A Cross-Lingual Mechanistic Analysis

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Rocchetti, Elisabetta, Ferrara, Alfio
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence I.2.7
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Unveiling Transformer Perception by Exploring Input Manifolds
by: Benfenati, Alessandro, et al.
Published: (2024)

InstructCMP: Length Control in Sentence Compression through Instruction-based Large Language Models
by: Juseon-Do, et al.
Published: (2024)

DeFTX: Denoised Sparse Fine-Tuning for Zero-Shot Cross-Lingual Transfer
by: Simon, Sona Elza, et al.
Published: (2025)

mEdIT: Multilingual Text Editing via Instruction Tuning
by: Raheja, Vipul, et al.
Published: (2024)

The Unreasonable Effectiveness of Model Merging for Cross-Lingual Transfer in LLMs
by: Bandarkar, Lucas, et al.
Published: (2025)

Mechanistic evaluation of Transformers and state space models
by: Arora, Aryaman, et al.
Published: (2025)

A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models
by: Rai, Daking, et al.
Published: (2024)

Text-Based Approaches to Item Difficulty Modeling in Large-Scale Assessments: A Systematic Review
by: Peters, Sydney, et al.
Published: (2025)

Zero-Shot Cross-Lingual Transfer using Prefix-Based Adaptation
by: A, Snegha, et al.
Published: (2025)

Considering Length Diversity in Retrieval-Augmented Summarization
by: Juseon-Do, et al.
Published: (2025)

RomanLens: The Role Of Latent Romanization In Multilinguality In LLMs
by: Saji, Alan, et al.
Published: (2025)

Instructional Agents: Reducing Teaching Faculty Workload through Multi-Agent Instructional Design
by: Yao, Huaiyuan, et al.
Published: (2025)

Beyond Token Length: Step Pruner for Efficient and Accurate Reasoning in Large Language Models
by: Wu, Canhui, et al.
Published: (2025)

How BERT Speaks Shakespearean English? Evaluating Historical Bias in Contextual Language Models
by: Cuscito, Miriam, et al.
Published: (2024)

Internal Reasoning vs. External Control: A Thermodynamic Analysis of Sycophancy in Large Language Models
by: Chang, Edward Y.
Published: (2025)

Instruction Complexity Induces Positional Collapse in Adversarial LLM Evaluation
by: Cacioli, Jon-Paul
Published: (2026)

Demystifying Instruction Mixing for Fine-tuning Large Language Models
by: Wang, Renxi, et al.
Published: (2023)

Attentive Reasoning Queries: A Systematic Method for Optimizing Instruction-Following in Large Language Models
by: Karov, Bar, et al.
Published: (2025)

Whether, Not Which: Mechanistic Interpretability Reveals Dissociable Affect Reception and Emotion Categorization in LLMs
by: Keeman, Michael
Published: (2026)

Separating Constraint Compliance from Semantic Accuracy: A Novel Benchmark for Evaluating Instruction-Following Under Compression
by: Baxi, Rahul
Published: (2025)

Efficient Toxicity Detection in Gaming Chats: A Comparative Study of Embeddings, Fine-Tuned Transformers and LLMs
by: Tereshchenko, Yehor, et al.
Published: (2025)

On the Effectiveness of LLM-Specific Fine-Tuning for Detecting AI-Generated Text
by: Gromadzki, Michał, et al.
Published: (2026)

Detecting AI-Generated Texts in Cross-Domains
by: Zhou, You, et al.
Published: (2024)

Fine-Tuned Large Language Models for Logical Translation: Reducing Hallucinations with Lang2Logic
by: Pan, Muyu, et al.
Published: (2025)

Improving Influence-based Instruction Tuning Data Selection for Balanced Learning of Diverse Capabilities
by: Dai, Qirun, et al.
Published: (2025)

Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification
by: Bucher, Martin Juan José, et al.
Published: (2024)

Presumed Cultural Identity: How Names Shape LLM Responses
by: Pawar, Siddhesh, et al.
Published: (2025)

Hallucination or Creativity: How to Evaluate AI-Generated Scientific Stories?
by: Argese, Alex, et al.
Published: (2026)

ProSwitch: Knowledge-Guided Instruction Tuning to Switch Between Professional and Non-Professional Responses
by: Zong, Chang, et al.
Published: (2024)

TRACE: Trajectory Correction from Cross-layer Evidence for Hallucination Reduction
by: Ranade, Tej Sanibh
Published: (2026)

More Is Not Always Better: Cross-Component Interference in LLM Agent Scaffolding
by: Liu, Ming
Published: (2026)

Old Habits Die Hard: How Conversational History Geometrically Traps LLMs
by: Simhi, Adi, et al.
Published: (2026)

Controllable Text Summarization: Unraveling Challenges, Approaches, and Prospects -- A Survey
by: Urlana, Ashok, et al.
Published: (2023)

Serialisation Strategy Matters: How FHIR Data Format Affects LLM Medication Reconciliation
by: Pator, Sanjoy
Published: (2026)

Beyond Prefixes: Graph-as-Memory Cross-Attention for Knowledge Graph Completion with Large Language Models
by: Liu, Ruitong, et al.
Published: (2025)

Raw Text is All you Need: Knowledge-intensive Multi-turn Instruction Tuning for Large Language Model
by: Hou, Xia, et al.
Published: (2024)

How to Evaluate Medical AI
by: Kopanichuk, Ilia, et al.
Published: (2025)

Evaluating the Efficacy of Hybrid Deep Learning Models in Distinguishing AI-Generated Text
by: Oketunji, Abiodun Finbarrs
Published: (2023)

USTCCTSU at SemEval-2024 Task 1: Reducing Anisotropy for Cross-lingual Semantic Textual Relatedness Task
by: Li, Jianjian, et al.
Published: (2024)

Seeing Through the Fog: A Cost-Effectiveness Analysis of Hallucination Detection Systems
by: Thomas, Alexander, et al.
Published: (2024)