Imagen de Portada

On the Paradoxical Interference between Instruction-Following and Task Solving

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Qi, Yunjia, Peng, Hao, Shi, Xintong, Xin, Amy, Wang, Xiaozhi, Xu, Bin, Hou, Lei, Li, Juanzi
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

VerIF: Verification Engineering for Reinforcement Learning in Instruction Following
por: Peng, Hao, et al.
Publicado: (2025)

Constraint Back-translation Improves Complex Instruction Following of Large Language Models
por: Qi, Yunjia, et al.
Publicado: (2024)

AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios
por: Qi, Yunjia, et al.
Publicado: (2025)

ADELIE: Aligning Large Language Models on Information Extraction
por: Qi, Yunjia, et al.
Publicado: (2024)

MAVEN-Fact: A Large-scale Event Factuality Detection Dataset
por: Li, Chunyang, et al.
Publicado: (2024)

StoryWriter: A Multi-Agent Framework for Long Story Generation
por: Xia, Haotian, et al.
Publicado: (2025)

StoryAlign: Evaluating and Training Reward Models for Story Generation
por: Xia, Haotian, et al.
Publicado: (2026)

Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems
por: Peng, Hao, et al.
Publicado: (2025)

WildReward: Learning Reward Models from In-the-Wild Human Interactions
por: Peng, Hao, et al.
Publicado: (2026)

OpenEP: Open-Ended Future Event Prediction
por: Guan, Yong, et al.
Publicado: (2024)

LLMAEL: Large Language Models are Good Context Augmenters for Entity Linking
por: Xin, Amy, et al.
Publicado: (2024)

Auxiliary Metrics Help Decoding Skill Neurons in the Wild
por: Zhao, Yixiu, et al.
Publicado: (2025)

Event-level Knowledge Editing
por: Peng, Hao, et al.
Publicado: (2024)

ChatLog: Carefully Evaluating the Evolution of ChatGPT Across Time
por: Tu, Shangqing, et al.
Publicado: (2023)

MRCEval: A Comprehensive, Challenging and Accessible Machine Reading Comprehension Benchmark
por: Ma, Shengkun, et al.
Publicado: (2025)

LinguaLens: Towards Interpreting Linguistic Mechanisms of Large Language Models via Sparse Auto-Encoder
por: Jing, Yi, et al.
Publicado: (2025)

Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons
por: Chen, Jianhui, et al.
Publicado: (2024)

TacoERE: Cluster-aware Compression for Event Relation Extraction
por: Guan, Yong, et al.
Publicado: (2024)

Preserving Knowledge Invariance: Rethinking Robustness Evaluation of Open Information Extraction
por: Qi, Ji, et al.
Publicado: (2023)

R-Eval: A Unified Toolkit for Evaluating Domain Knowledge of Retrieval Augmented Large Language Models
por: Tu, Shangqing, et al.
Publicado: (2024)

VidCoM: Fast Video Comprehension through Large Language Models with Multimodal Tools
por: Qi, Ji, et al.
Publicado: (2023)

LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks
por: Bai, Yushi, et al.
Publicado: (2024)

Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders
por: Jing, Yi, et al.
Publicado: (2026)

MAVEN-Arg: Completing the Puzzle of All-in-One Event Understanding Dataset with Event Argument Annotation
por: Wang, Xiaozhi, et al.
Publicado: (2023)

AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge Reasoning
por: Xin, Amy, et al.
Publicado: (2024)

Precise Localization of Memories: A Fine-grained Neuron-level Knowledge Editing Technique for LLMs
por: Pan, Haowen, et al.
Publicado: (2025)

Pre-training Language Model Incorporating Domain-specific Heterogeneous Knowledge into A Unified Representation
por: Zhu, Hongyin, et al.
Publicado: (2021)

WebSeer: Training Deeper Search Agents through Reinforcement Learning with Self-Reflection
por: He, Guanzhong, et al.
Publicado: (2025)

MM-MATH: Advancing Multimodal Math Evaluation with Process Evaluation and Fine-grained Classification
por: Sun, Kai, et al.
Publicado: (2024)

Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards
por: Zhang, Jiajie, et al.
Publicado: (2026)

Pre-training Distillation for Large Language Models: A Design Space Exploration
por: Peng, Hao, et al.
Publicado: (2024)

Instruction-Following Pruning for Large Language Models
por: Hou, Bairu, et al.
Publicado: (2025)

StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets?
por: Chen, Yanxu, et al.
Publicado: (2025)

Layer-Aware Task Arithmetic: Disentangling Task-Specific and Instruction-Following Knowledge
por: Chen, Yan-Lun, et al.
Publicado: (2025)

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

KoLA: Carefully Benchmarking World Knowledge of Large Language Models
por: Yu, Jifan, et al.
Publicado: (2023)

Boundary-Guided Policy Optimization for Memory-efficient RL of Diffusion Large Language Models
por: Lin, Nianyi, et al.
Publicado: (2025)

Dancing in Chains: Reconciling Instruction Following and Faithfulness in Language Models
por: Wu, Zhengxuan, et al.
Publicado: (2024)

Event GDR: Event-Centric Generative Document Retrieval
por: Guan, Yong, et al.
Publicado: (2024)

DeepPrune: Parallel Scaling without Inter-trace Redundancy
por: Tu, Shangqing, et al.
Publicado: (2025)