Imagen de Portada

Rethinking Table Instruction Tuning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Deng, Naihao, Mihalcea, Rada
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Are Human Interactions Replicable by Generative Agents? A Case Study on Pronoun Usage in Hierarchical Interactions
por: Deng, Naihao, et al.
Publicado: (2025)

Benchmarking and Improving LLM Robustness for Personalized Generation
por: Okite, Chimaobi, et al.
Publicado: (2025)

$R^3$: "This is My SQL, Are You With Me?" A Consensus-Based Multi-Agent System for Text-to-SQL Tasks
por: Xia, Hanchen, et al.
Publicado: (2024)

Tables as Texts or Images: Evaluating the Table Reasoning Ability of LLMs and MLLMs
por: Deng, Naihao, et al.
Publicado: (2024)

SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models
por: Torres-Fonseca, Josue, et al.
Publicado: (2026)

Chumor 2.0: Towards Benchmarking Chinese Humor Understanding
por: He, Ruiqi, et al.
Publicado: (2024)

Mind the (Belief) Gap: Group Identity in the World of LLMs
por: Borah, Angana, et al.
Publicado: (2025)

MAiDE-up: Multilingual Deception Detection of GPT-generated Hotel Reviews
por: Ignat, Oana, et al.
Publicado: (2024)

Cross-cultural Inspiration Detection and Analysis in Real and LLM-generated Social Media Data
por: Ignat, Oana, et al.
Publicado: (2024)

DOTRAG: Retrieval-Time Reasoning Along Paths
por: Moore, Larnell, et al.
Publicado: (2026)

Table as Thought: Exploring Structured Thoughts in LLM Reasoning
por: Sun, Zhenjie, et al.
Publicado: (2025)

One Word at a Time: Incremental Completion Decomposition Breaks LLM Safety
por: Arif, Samee, et al.
Publicado: (2026)

Towards Algorithmic Fidelity: Mental Health Representation across Demographics in Synthetic vs. Human-generated Data
por: Mori, Shinka, et al.
Publicado: (2024)

Belief-Sim: Towards Belief-Driven Simulation of Demographic Misinformation Susceptibility
por: Borah, Angana, et al.
Publicado: (2026)

VERVE: Template-based ReflectiVE Rewriting for MotiVational IntErviewing
por: Min, Do June, et al.
Publicado: (2023)

CliniDial: A Naturally Occurring Multimodal Dialogue Dataset for Team Reflection in Action During Clinical Operation
por: Deng, Naihao, et al.
Publicado: (2025)

The Power of Many: Multi-Agent Multimodal Models for Cultural Image Captioning
por: Bai, Longju, et al.
Publicado: (2024)

Annotations on a Budget: Leveraging Geo-Data Similarity to Balance Model Performance and Annotation Cost
por: Ignat, Oana, et al.
Publicado: (2024)

A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity
por: Lee, Andrew, et al.
Publicado: (2024)

The Generation Gap: Exploring Age Bias in the Value Systems of Large Language Models
por: Liu, Siyang, et al.
Publicado: (2024)

When Ethics and Payoffs Diverge: LLM Agents in Morally Charged Social Dilemmas
por: Backmann, Steffen, et al.
Publicado: (2025)

SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests
por: Pandey, Punya Syon, et al.
Publicado: (2025)

Deception Detection from Linguistic and Physiological Data Streams Using Bimodal Convolutional Neural Networks
por: Li, Panfeng, et al.
Publicado: (2023)

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

Uplifting Lower-Income Data: Strategies for Socioeconomic Perspective Shifts in Large Multi-modal Models
por: Nwatu, Joan, et al.
Publicado: (2024)

Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction
por: Fu, Tingchen, et al.
Publicado: (2024)

Voices of Her: Analyzing Gender Differences in the AI Publication World
por: Ding, Yiwen, et al.
Publicado: (2023)

Culture Affordance Atlas: Reconciling Object Diversity Through Functional Mapping
por: Nwatu, Joan, et al.
Publicado: (2025)

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

Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models
por: Ignat, Oana, et al.
Publicado: (2023)

Not All Documents Are What You Need for Extracting Instruction Tuning Data
por: Zhang, Chi, et al.
Publicado: (2025)

Federated Data-Efficient Instruction Tuning for Large Language Models
por: Qin, Zhen, et al.
Publicado: (2024)

Eeyore: Realistic Depression Simulation via Supervised and Preference Optimization
por: Liu, Siyang, et al.
Publicado: (2025)

Stronger Models are NOT Stronger Teachers for Instruction Tuning
por: Xu, Zhangchen, et al.
Publicado: (2024)

Controllable Text Generation in the Instruction-Tuning Era
por: Ashok, Dhananjay, et al.
Publicado: (2024)

A Closer Look at the Limitations of Instruction Tuning
por: Ghosh, Sreyan, et al.
Publicado: (2024)

SwitchCIT: Switching for Continual Instruction Tuning
por: Wu, Xinbo, et al.
Publicado: (2024)

Can Large Language Models Infer Causation from Correlation?
por: Jin, Zhijing, et al.
Publicado: (2023)

Bridging Writing Manner Gap in Visual Instruction Tuning by Creating LLM-aligned Instructions
por: Jing, Dong, et al.
Publicado: (2025)

Chord Embeddings: Analyzing What They Capture and Their Role for Next Chord Prediction and Artist Attribute Prediction
por: Lahnala, Allison, et al.
Publicado: (2021)