Copertina

Does Instruction Tuning Make LLMs More Consistent?

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Fierro, Constanza, Li, Jiaang, Søgaard, Anders
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Factual Consistency of Multilingual Pretrained Language Models
di: Fierro, Constanza, et al.
Pubblicazione: (2022)

Do Vision and Language Models Share Concepts? A Vector Space Alignment Study
di: Li, Jiaang, et al.
Pubblicazione: (2023)

How Do Multilingual Language Models Remember Facts?
di: Fierro, Constanza, et al.
Pubblicazione: (2024)

Defining Knowledge: Bridging Epistemology and Large Language Models
di: Fierro, Constanza, et al.
Pubblicazione: (2024)

MuLan: A Study of Fact Mutability in Language Models
di: Fierro, Constanza, et al.
Pubblicazione: (2024)

Concept Space Alignment in Multilingual LLMs
di: Peng, Qiwei, et al.
Pubblicazione: (2024)

Learning To See But Forgetting To Follow: Visual Instruction Tuning Makes LLMs More Prone To Jailbreak Attacks
di: Pantazopoulos, Georgios, et al.
Pubblicazione: (2024)

Evaluating Adjective-Noun Compositionality in LLMs: Functional vs Representational Perspectives
di: Dhar, Ruchira, et al.
Pubblicazione: (2026)

Evaluation Revisited: A Taxonomy of Evaluation Concerns in Natural Language Processing
di: Dhar, Ruchira, et al.
Pubblicazione: (2026)

Revisiting the Othello World Model Hypothesis
di: Yuan, Yifei, et al.
Pubblicazione: (2025)

Comprehensive Reassessment of Large-Scale Evaluation Outcomes in LLMs: A Multifaceted Statistical Approach
di: Sun, Kun, et al.
Pubblicazione: (2024)

Debiasing Multilingual LLMs in Cross-lingual Latent Space
di: Peng, Qiwei, et al.
Pubblicazione: (2025)

From Words to Worlds: Compositionality for Cognitive Architectures
di: Dhar, Ruchira, et al.
Pubblicazione: (2024)

Mechanistic Interpretability Needs Philosophy
di: Williams, Iwan, et al.
Pubblicazione: (2025)

Exploring Format Consistency for Instruction Tuning
di: Liang, Shihao, et al.
Pubblicazione: (2023)

Steering Language Models with Weight Arithmetic
di: Fierro, Constanza, et al.
Pubblicazione: (2025)

FoodieQA: A Multimodal Dataset for Fine-Grained Understanding of Chinese Food Culture
di: Li, Wenyan, et al.
Pubblicazione: (2024)

RAVENEA: A Benchmark for Multimodal Retrieval-Augmented Visual Culture Understanding
di: Li, Jiaang, et al.
Pubblicazione: (2025)

Less is More: High-value Data Selection for Visual Instruction Tuning
di: Liu, Zikang, et al.
Pubblicazione: (2024)

Instruction Tuning and CoT Prompting for Contextual Medical QA with LLMs
di: Le, Chenqian, et al.
Pubblicazione: (2025)

SCE: Scalable Consistency Ensembles Make Blackbox Large Language Model Generation More Reliable
di: Zhang, Jiaxin, et al.
Pubblicazione: (2025)

mCoT: Multilingual Instruction Tuning for Reasoning Consistency in Language Models
di: Lai, Huiyuan, et al.
Pubblicazione: (2024)

Hierarchical Alignment: Enforcing Hierarchical Instruction-Following in LLMs through Logical Consistency
di: Yang, Shu, et al.
Pubblicazione: (2026)

Instruction-Tuning LLMs for Event Extraction with Annotation Guidelines
di: Srivastava, Saurabh, et al.
Pubblicazione: (2025)

Are Economists Always More Introverted? Analyzing Consistency in Persona-Assigned LLMs
di: Reusens, Manon, et al.
Pubblicazione: (2025)

Unlocking Markets: A Multilingual Benchmark to Cross-Market Question Answering
di: Yuan, Yifei, et al.
Pubblicazione: (2024)

WebQAmGaze: A Multilingual Webcam Eye-Tracking-While-Reading Dataset
di: Ribeiro, Tiago, et al.
Pubblicazione: (2023)

Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?
di: Gekhman, Zorik, et al.
Pubblicazione: (2024)

What Makes Good Instruction-Tuning Data? An In-Context Learning Perspective
di: Han, Guangzeng, et al.
Pubblicazione: (2026)

Balancing Continuous Pre-Training and Instruction Fine-Tuning: Optimizing Instruction-Following in LLMs
di: Jindal, Ishan, et al.
Pubblicazione: (2024)

The Atomic Instruction Gap: Instruction-Tuned LLMs Struggle with Simple, Self-Contained Directives
di: Lim, Henry, et al.
Pubblicazione: (2025)

Understanding Subword Compositionality of Large Language Models
di: Peng, Qiwei, et al.
Pubblicazione: (2025)

Tool Calling for Arabic LLMs: Data Strategies and Instruction Tuning
di: Ersoy, Asim, et al.
Pubblicazione: (2025)

Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning
di: Zhao, Hao, et al.
Pubblicazione: (2024)

What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction Tuning
di: Du, Yifan, et al.
Pubblicazione: (2023)

From Output to Evaluation: Does Raw Instruction-Tuned Code LLMs Output Suffice for Fill-in-the-Middle Code Generation?
di: Ahmad, Wasi Uddin, et al.
Pubblicazione: (2025)

Instruction Fine-Tuning: Does Prompt Loss Matter?
di: Huerta-Enochian, Mathew, et al.
Pubblicazione: (2024)

Cross-Task Defense: Instruction-Tuning LLMs for Content Safety
di: Fu, Yu, et al.
Pubblicazione: (2024)

Facilitating Multi-turn Function Calling for LLMs via Compositional Instruction Tuning
di: Chen, Mingyang, et al.
Pubblicazione: (2024)

BioMistral-NLU: Towards More Generalizable Medical Language Understanding through Instruction Tuning
di: Fu, Yujuan Velvin, et al.
Pubblicazione: (2024)