Instruction Following

Follow this topic Ask about this topic

Momentum

11 papers in the last four weeks, down 8% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 85

All topics

SyRuP: Enhancing System-Prompt Following via Reward-Guided Prediction in LLM Decoding
Jul 27, 2026Seoyeon Kim, Minjae Kang, Jaehyung KimLanguage Model Decoding Language Model Steering
Yonsei University
Task Competence Is Not Instruction Following: Evaluating Instruction-Conflicting Behavior in Small Language Models
Jul 21, 2026Mahdiyeh Farajidizaji, Vatsal RainaLLM Evaluation Instruction Following
Khajeh Nasir Toosi University of Technology · Apta AI, Spark AI Research
Prompt Design at Scale: How Format, Instruction Count, and Context Length Shape Instruction Adherence and Hallucination in Large Language Models
Jul 21, 2026Netanel EliavLLM Evaluation Language Model Generation Evaluation
Machine Human Intelligence Lab (MHIL)
Compile, Then Page: Executable SOP Programs and a Capability-Gated Runtime for Procedural LLM Agents
Jul 13, 2026Chenglin Yu, Li Yin, Ying Yu +4Instruction Following Runtime Enforcement for AI Agents
Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University · Department of Data and Systems Engineering, The University of Hong Kong · College of Economics and Management, Zhejiang Normal University +3
Unlocking Speech-Text Compositional Powers: Instruction-Following Speech Language Models without Instruction Tuning
Jul 2, 2026Congrui Du, Yang Zhang, Kaizhi Qian +1Language Model Pretraining Instruction Following
University of California, Santa Barbara, USA · MIT-IBM Computing Research Lab, IBM Research, USA
Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity
Jun 30, 2026Bytedance SeedLLM Evaluation Instruction Following
Bytedance Seed
CDR-Bench: Evaluating Faithful Execution of Compositional, Order-Sensitive Data Refinement Recipes
Jun 30, 2026Yuchen Huang, Xiang Li, Zhenqing Ling +5LLM Evaluation Instruction Following
1HKUST · 2NUS · 3Tongyi Lab , Alibaba Group
Indi-RomCoM: Code-Mixed Benchmark for Evaluating LLMs on Romanized Indic-English Instructions
Jun 29, 2026Avisha Das, Mihir Parmar, Mohana Ramnath +1Multilingual Language Model Evaluation Instruction Following
Shiv Nadar University Chennai · Google Cloud AI Research · IIT Madras
IHDec: Divergence-Steered Contrastive Decoding for Securing Multi-Turn Instruction Hierarchies
Jun 29, 2026Nicole Geumheon Liu, Haeun Jang, Yonghyun Jun +1Instruction Following Prompt Injection Defense
Chung-Ang University, Seoul, Korea
Are Humans Evolved Instruction Followers? An Underlying Inductive Bias Enables Rapid Instructed Task Learning
Jun 29, 2026Anjishnu KumarInstruction Following Inductive Bias
Amazon Alexa AI Seattle, USA
Masked Language Flow Models
Jun 26, 2026Iskander Azangulov, Kianoosh Ashouritaklimi, Leo Zhang +2Masked Diffusion Models Instruction Following
Department of Statistics, University of Oxford
FBK's Long-form SpeechLLMs for IWSLT 2026 Instruction Following
Jun 25, 2026Zhihang Xie, Marco Gaido, Sara Papi +2Audio-Language Model Evaluation Speech Processing
Fondazione Bruno Kessler · University of Trento
A Framework for Evaluating Agentic Skills at Scale
Jun 16, 2026Maksim Shaposhnikov, Nicolas Fortuin, Simon Stipcich +3LLM Agent Evaluation Instruction Following
Tessl London, United Kingdom
Beyond English: Uncovering the Multilingual Gap in Vision-Language-Action Models
Jun 14, 2026Hanyang Chen, Hongliang Li, Jiarui Cao +6Cross-Lingual Representation Alignment Instruction Following
Beijing Jiaotong University
Soft-Prompt Tuning for Fair and Efficient LLM Benchmark Evaluation
Jun 10, 2026Selen Erkan, Bastian Boll, Kristian Kersting +2LLM Evaluation Instruction Following
Aleph Alpha Research Lab1141 · TU Darmstadt Hessian.AI Lab1141
When Built-in Thinking Helps and Hurts: Constraint-Level Error Shifts in Instruction Following
Jun 8, 2026Sai Adith Senthil KumarLLM Evaluation Instruction Following
George Mason University
ComplexConstraints and Beyond: Expert Rubrics for RLVR
Jun 8, 2026Sushant Mehta, Liudas Panavas, Suhaas Garre +1LLM-as-a-Judge Rubric-Based RL
Surge AI
Where Instruction Hierarchy Breaks: Diagnosing and Repairing Failures in Reasoning Language Models
Jun 5, 2026Sanjay Kariyappa, G. Edward SuhLLM Auditing Instruction Following
NVIDIA
RECAP: Regression Evaluation for Continual Adaptation of Prompts
Jun 4, 2026Harsh Deshpande, Kushal Chawla, Sangwoo Cho +2Continual Learning for LLMs LLM Evaluation
Capital One
MDP-GRPO: Stabilized Group Relative Policy Optimization for Multi-Constraint Instruction Following
Jun 4, 2026Mohammad Mahdi Salmani-Zarchi, Zahra Rahimi, Heshaam Faili +1Group Relative Policy Optimization Instruction Following
Department of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran · Department of Statistics, Mathematics and Computer Science, Allameh Tabataba’i University, Tehran, Iran
Multilingual Long-Form Speech Instruction Following: KIT's Submission to IWSLT 2026
Jun 3, 2026Enes Yavuz Ugan, Maike Züfle, Yuka Ko +5MBR Decoding Instruction Following
1Karlsruhe Institute of Technology · 2Carnegie Mellon University
Bridging Auxiliary Constraints to Resolve Instruction Following in Large Reasoning Models
Jun 2, 2026Zhengyi Zhao, Shubo Zhang, Huimin Wang +7LLM Prompting Instruction Following
The Chinese University of Hong Kong · Tencent Jarvis Lab · Westlake University +2
AnyAudio-Judge: A Dynamic Rubric-Based Benchmark and Evaluator for Audio Instruction Following
Jun 2, 2026Haitao Li, Tian Tan, Yuguang Yang +2Audio-Language Model Evaluation LLM-as-a-Judge
Zhejiang University · Shanghai Innovation Institute · Shanghai Jiao Tong University +1
Label-Free Reinforcement Learning via Cross-Model Entropy
May 27, 2026Matt Gorbett, Hossein ShiraziReinforcement Learning Instruction Following
Independent Researcher · San Diego State University
Soft-SVeRL: Self-Verified Reinforcement Learning with Soft Rewards
May 27, 2026Saurabh Dash, Pierre Clavier, John Dang +4Reinforcement Learning Instruction Following
Cohere Labs · Cohere · Adaption Labs +1
The Missing Piece in Pre-trained Model Evaluation: Reward-Guided Decoding Unlocks Task-Oriented Behavior Without Parameter Updates
May 27, 2026Shaobo Wang, Guo Chen, Ziyue Wang +5LLM Evaluation Language Model Decoding
Shanghai Jiao Tong University · Qwen Team, Alibaba Group · The Chinese University of Hong Kong, Shenzhen
Disentangling Language Roles in Multilingual LLM Task Execution
May 26, 2026Qishi Zhan, Minxuan Hu, Seoyeon Jang +7Multilingual Language Models Multilingual Language Model Evaluation
Marquette · Cornell · UC San Diego +7
MAIGO: Mitigating Lost-in-Conversation with History-Cleaned On-Policy Self-Distillation
May 26, 2026Haoyu Zheng, Yun Zhu, Shu Yuan +5Instruction Following Data Contamination in Language Models
1Zhejiang University · 2Shanghai AI Laboratory · 3Huazhong University of Science and Technology +2
ContextGuard: Structured Self-Auditing for Context Learning in Language Models
May 26, 2026Hongbo Jin, Chi Wang, Haoran Tang +5LLM Auditing Instruction Following
Peking University · SCUT · Tsinghua University
Do as I Say, Not as I Do: Instruction-Induction Conflict in LLMs
May 19, 2026Carolina Camassa, Derek ShillerLLM Evaluation Language Model Self-Assessment
Future Impact Group · Rethink Priorities

Jul 27, 2026, cs.CLJ/K move · Enter open · S save

SyRuP: Enhancing System-Prompt Following via Reward-Guided Prediction in LLM Decoding

Seoyeon Kim, Minjae Kang, Jaehyung Kim

Yonsei University

Language Model Decoding Language Model Steering Instruction Following

Open paper AskPDF arXiv

Large Language Models (LLMs) are increasingly controlled through system prompts that specify roles, formats, and safety requirements. However, models follow these prompts only implicitly through in-context learning, which can be insufficient for complex or compositional prompts. Existing approaches often require model tuning or response-level reranking, limiting their practicality for lightweight inference-time control. We introduce SyRuP, a decoding-time framework for improving system-prompt adherence while keeping the base LM frozen. SyRuP trains a cross-attention reward head from system-prompt-conditioned preference pairs, treating the system prompt as a separate memory to produce token-level adherence scores. At inference, SyRuP reranks the base LM's top-k candidates by combining base logits with both the learned reward signal and a contrastive signal that captures system-induced logit shifts. Experiments on system-prompt following benchmarks show that SyRuP consistently outperforms prompting and decoding-time baselines with moderate inference overhead. These results suggest that explicit token-level guidance is an effective and practical mechanism for reliable system-prompt following.

Momentum

Related topics

Latest papers 85