Buchumschlag

LARFT: Closing the Cognition-Action Gap for Length Instruction Following in Large Language Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Zhang, Wei, Du, Lintong, Zhang, Yuanhe, Zhou, Zhenhong, Wang, Kun, Sun, Li, Su, Sen
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Computation and Language Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

LIFEBench: Evaluating Length Instruction Following in Large Language Models
von: Zhang, Wei, et al.
Veröffentlicht: (2025)

Resource Consumption Threats in Large Language Models
von: Zhang, Yuanhe, et al.
Veröffentlicht: (2026)

CORBA: Contagious Recursive Blocking Attacks on Multi-Agent Systems Based on Large Language Models
von: Zhou, Zhenhong, et al.
Veröffentlicht: (2025)

Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings
von: Zhang, Yuanhe, et al.
Veröffentlicht: (2024)

LexInstructEval: Lexical Instruction Following Evaluation for Large Language Models
von: Ren, Huimin, et al.
Veröffentlicht: (2025)

Speak Out of Turn: Safety Vulnerability of Large Language Models in Multi-turn Dialogue
von: Zhou, Zhenhong, et al.
Veröffentlicht: (2024)

Beyond Instruction Following: Evaluating Inferential Rule Following of Large Language Models
von: Sun, Wangtao, et al.
Veröffentlicht: (2024)

RefuteBench: Evaluating Refuting Instruction-Following for Large Language Models
von: Yan, Jianhao, et al.
Veröffentlicht: (2024)

DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based Agent
von: Zhu, Pengyu, et al.
Veröffentlicht: (2025)

Alignment-Enhanced Decoding:Defending via Token-Level Adaptive Refining of Probability Distributions
von: Liu, Quan, et al.
Veröffentlicht: (2024)

Closing the Confidence-Faithfulness Gap in Large Language Models
von: Miao, Miranda Muqing, et al.
Veröffentlicht: (2026)

Revisiting the Reliability of Language Models in Instruction-Following
von: Dong, Jianshuo, et al.
Veröffentlicht: (2025)

The Instruction Gap: LLMs get lost in Following Instruction
von: Tripathi, Vishesh, et al.
Veröffentlicht: (2025)

CIF-Bench: A Chinese Instruction-Following Benchmark for Evaluating the Generalizability of Large Language Models
von: LI, Yizhi, et al.
Veröffentlicht: (2024)

Optimizing Psychological Counseling with Instruction-Tuned Large Language Models
von: Li, Wenjie, et al.
Veröffentlicht: (2024)

The Impact of Reasoning Step Length on Large Language Models
von: Jin, Mingyu, et al.
Veröffentlicht: (2024)

DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models
von: Li, Zherui, et al.
Veröffentlicht: (2025)

Instruction Tuning for Large Language Models: A Survey
von: Zhang, Shengyu, et al.
Veröffentlicht: (2023)

MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction-Following
von: Lou, Renze, et al.
Veröffentlicht: (2023)

Phased Instruction Fine-Tuning for Large Language Models
von: Pang, Wei, et al.
Veröffentlicht: (2024)

Detoxification of Large Language Models through Output-layer Fusion with a Calibration Model
von: Tian, Yuanhe, et al.
Veröffentlicht: (2025)

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

E^2-LLM: Efficient and Extreme Length Extension of Large Language Models
von: Liu, Jiaheng, et al.
Veröffentlicht: (2024)

Countering Catastrophic Forgetting of Large Language Models for Better Instruction Following via Weight-Space Model Merging
von: Lyu, Mengxian, et al.
Veröffentlicht: (2026)

GraphGPT: Graph Instruction Tuning for Large Language Models
von: Tang, Jiabin, et al.
Veröffentlicht: (2023)

Aligning Large Language Models to Follow Instructions and Hallucinate Less via Effective Data Filtering
von: Si, Shuzheng, et al.
Veröffentlicht: (2025)

InFoBench: Evaluating Instruction Following Ability in Large Language Models
von: Qin, Yiwei, et al.
Veröffentlicht: (2024)

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

Conifer: Improving Complex Constrained Instruction-Following Ability of Large Language Models
von: Sun, Haoran, et al.
Veröffentlicht: (2024)

Contrastive Learning for Knowledge-Based Question Generation in Large Language Models
von: Zhang, Zhenhong, et al.
Veröffentlicht: (2024)

MulDimIF: A Multi-Dimensional Constraint Framework for Evaluating and Improving Instruction Following in Large Language Models
von: Ye, Junjie, et al.
Veröffentlicht: (2025)

LangGap: Diagnosing and Closing the Language Gap in Vision-Language-Action Models
von: Hou, Yuchen, et al.
Veröffentlicht: (2026)

Instruction Following by Principled Boosting Attention of Large Language Models
von: Guardieiro, Vitoria, et al.
Veröffentlicht: (2025)

Revisiting Compositional Generalization Capability of Large Language Models Considering Instruction Following Ability
von: Sakai, Yusuke, et al.
Veröffentlicht: (2025)

KITE: A Benchmark for Evaluating Korean Instruction-Following Abilities in Large Language Models
von: Kim, Dongjun, et al.
Veröffentlicht: (2025)

From Helpfulness to Toxic Proactivity: Diagnosing Behavioral Misalignment in LLM Agents
von: Wang, Xinyue, et al.
Veröffentlicht: (2026)

Self-Cognition in Large Language Models: An Exploratory Study
von: Chen, Dongping, et al.
Veröffentlicht: (2024)

On the Role of Attention Heads in Large Language Model Safety
von: Zhou, Zhenhong, et al.
Veröffentlicht: (2024)

Finetuning Generative Large Language Models with Discrimination Instructions for Knowledge Graph Completion
von: Liu, Yang, et al.
Veröffentlicht: (2024)

CodeIF-Bench: Evaluating Instruction-Following Capabilities of Large Language Models in Interactive Code Generation
von: Wang, Peiding, et al.
Veröffentlicht: (2025)