Imagen de Portada

Decoupling Task-Solving and Output Formatting in LLM Generation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Deng, Haikang, Kung, Po-Nien, Peng, Nanyun
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Adaptable Logical Control for Large Language Models
por: Zhang, Honghua, et al.
Publicado: (2024)

STAR: Boosting Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language Models
por: Ma, Mingyu Derek, et al.
Publicado: (2023)

LLM-REVal: Can We Trust LLM Reviewers Yet?
por: Li, Rui, et al.
Publicado: (2025)

Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model
por: Deng, Haikang, et al.
Publicado: (2023)

Improving Event Definition Following For Zero-Shot Event Detection
por: Cai, Zefan, et al.
Publicado: (2024)

DialectGen: Benchmarking and Improving Dialect Robustness in Multimodal Generation
por: Zhou, Yu, et al.
Publicado: (2025)

AMRFact: Enhancing Summarization Factuality Evaluation with AMR-Driven Negative Samples Generation
por: Qiu, Haoyi, et al.
Publicado: (2023)

GenEARL: A Training-Free Generative Framework for Multimodal Event Argument Role Labeling
por: Bansal, Hritik, et al.
Publicado: (2024)

Multimodal Cultural Safety: Evaluation Framework and Alignment Strategies
por: Qiu, Haoyi, et al.
Publicado: (2025)

Evaluating Cultural and Social Awareness of LLM Web Agents
por: Qiu, Haoyi, et al.
Publicado: (2024)

Structured Outputs Enable General-Purpose LLMs to be Medical Experts
por: Guo, Guangfu, et al.
Publicado: (2025)

DRS: Deep Question Reformulation With Structured Output
por: Li, Zhecheng, et al.
Publicado: (2024)

Policy Frameworks for Transparent Chain-of-Thought Reasoning in Large Language Models
por: Chen, Yihang, et al.
Publicado: (2025)

Guiding Through Complexity: What Makes Good Supervision for Hard Math Reasoning Tasks?
por: He, Xuan, et al.
Publicado: (2024)

SafeWorld: Geo-Diverse Safety Alignment
por: Yin, Da, et al.
Publicado: (2024)

LLM Output Detectability and Task Performance Can be Jointly Optimized
por: Saito, Koshiro, et al.
Publicado: (2026)

Evaluating Human Alignment and Model Faithfulness of LLM Rationale
por: Fayyaz, Mohsen, et al.
Publicado: (2024)

Detecting Machine-Generated Long-Form Content with Latent-Space Variables
por: Tian, Yufei, et al.
Publicado: (2024)

A Course Shared Task on Evaluating LLM Output for Clinical Questions
por: Hou, Yufang, et al.
Publicado: (2024)

LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs
por: Long, Do Xuan, et al.
Publicado: (2024)

MMPersuade: A Dataset and Evaluation Framework for Multimodal Persuasion
por: Qiu, Haoyi, et al.
Publicado: (2025)

DeCode: Decoupling Content and Delivery for Medical QA
por: Ko, Po-Jen, et al.
Publicado: (2026)

Learning Structured Reasoning via Tractable Trajectory Control
por: Kung, Po-Nien, et al.
Publicado: (2026)

Scientific Discourse Tagging for Evidence Extraction
por: Li, Xiangci, et al.
Publicado: (2019)

A Paragraph-level Multi-task Learning Model for Scientific Fact-Verification
por: Li, Xiangci, et al.
Publicado: (2020)

Task-Dependent Evaluation of LLM Output Homogenization: A Taxonomy-Guided Framework
por: Jain, Shomik, et al.
Publicado: (2025)

OpenVLThinkerV2: A Generalist Multimodal Reasoning Model for Multi-domain Visual Tasks
por: Hu, Wenbo, et al.
Publicado: (2026)

TDR: Task-Decoupled Retrieval with Fine-Grained LLM Feedback for In-Context Learning
por: Chen, Yifu, et al.
Publicado: (2025)

TOD-ProcBench: Benchmarking Complex Instruction-Following in Task-Oriented Dialogues
por: Ghazarian, Sarik, et al.
Publicado: (2025)

StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving
por: Gao, Chang, et al.
Publicado: (2023)

On the Loss of Context-awareness in General Instruction Fine-tuning
por: Wang, Yihan, et al.
Publicado: (2024)

Decoupling Knowledge and Task Subspaces for Composable Parametric Retrieval Augmented Generation
por: Su, Weihang, et al.
Publicado: (2026)

Enhancing LLM Character-Level Manipulation via Divide and Conquer
por: Xiong, Zhen, et al.
Publicado: (2025)

Synchronous Faithfulness Monitoring for Trustworthy Retrieval-Augmented Generation
por: Wu, Di, et al.
Publicado: (2024)

On the Paradoxical Interference between Instruction-Following and Task Solving
por: Qi, Yunjia, et al.
Publicado: (2026)

MMGR: Multi-Modal Generative Reasoning
por: Cai, Zefan, et al.
Publicado: (2025)

FMBench: Adaptive Large Language Model Output Formatting
por: Wang, Yaoting, et al.
Publicado: (2026)

SkillVerse : Assessing and Enhancing LLMs with Tree Evaluation
por: Tian, Yufei, et al.
Publicado: (2025)

Output-Space Search: Targeting LLM Generations in a Frozen Encoder-Defined Output Space
por: Materzok, Tobias
Publicado: (2026)

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