Instruction-Tuned Models

Ask about this topic

Momentum

17 papers in the last four weeks, up 55% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 158

All topics
CardsList

  1. Principled Under Pressure: Post-Training Decides Whether LLMs Act on Their Own Moral Judgment

    Oct 6, 2026Orion Reblitz-RichardsonInstruction-Tuned Models

    Distiller Labs

  2. Does Steering Break Your Model? A Multi-Dimensional Evaluation Suite for LLM Steering Methods

    Oct 6, 2026Haotian Yang, Huikang Jiang, Yucheng Wu +4Linear Activation SteeringLarge Language Model Evaluation

    State Key Laboratory of Multimedia Information Processing, Peking University · School of Computer Science, Peking University · Columbia University +2

  3. Base Models Can Reason By Taking a Cue From Training Data

    Oct 5, 2026Sophie L. Wang, Amil Dravid, Rulin Shao +3Instruction-Tuned Models

    MIT · UC Berkeley · University of Washington +1

  4. You Changed Your Mind, The Model Didn't: Demystifying Intent in Multi-Turn Dialogue

    Oct 5, 2026Junle Chen, Wei Chen, Zhengjun Huang +5Multi-Turn InteractionsInstruction-Tuned Models

    HKUST · Tencent

  5. The Assistance Dilemma: Learning to Teach via Multi-Turn Reinforcement Learning

    Oct 5, 2026Jakub Macina, Manu Kapur, Mrinmaya SachanTutorsLarge Language Model Reinforcement Learning

    ETH Zurich

  6. Steering by Influence: Curvature Aware Data Weighting for Activation Steering

    Oct 5, 2026James A. E. Dixon, Stephen J. Roberts, Francesco QuinzanLinear Activation SteeringModel Activations

    Machine Learning Research Group, Department of Engineering Science University of Oxford

  7. Lend Me Your Eyes: Instruction-Aware Text Embeddings via Attention Relay

    Oct 4, 2026Yiyuan Luo, Vaggos ChatziafratisInstruction-Tuned Models

    University of California, Santa Cruz

  8. Hidden in the Comments: A Context-Injection Attack Surface in Code LLMs

    Oct 4, 2026Noor Munir, Francesco Quinzan, Stephen RobertsInstruction Injection AttacksInstruction-Tuned Models

    Department of Engineering Science, University of Oxford, Oxford OX1 3PJ, UK

  9. AnyJev Technical Report

    Sep 30, 2026Jiamu Zhang, Tianze Yang, Yucheng Shi +6Instruction-Tuned ModelsDecisions

    Nokia, Sunnyvale, CA, USA · Tencent Hunyuan · The Hong Kong Polytechnic University

  10. Coverage Before Control: Route-Instruction Grounding and Steering for Controllable Retrosynthesis

    Sep 30, 2026Xuemin Chen, Xiaozhuang Song, Xinjian Zhao +2InstructionInstruction-Tuned Models

    The Chinese University of Hong Kong, Shenzhen

  11. OPSRD: On-Policy Self-Role Distillation

    Sep 30, 2026Weijie Ren, Yanwen Zhang, Hao Li +3Unsupervised On-Policy Self-DistillationInstruction-Tuned Models

    Zhejiang University · University of Electronic Science and Technology of China · University of Science and Technology of China

  12. The Safety Operator: Modulating the Expression of Safety Instructions via Spectral Optimization

    Sep 29, 2026Benoit Dherin, Michael Munn, Xavier Gonzalvo +14Safety ClaimsInstruction Tuning

    Google Research · Cambridge University · Google DeepMind +2

  13. Same Bytes, Different Authority: Reserved-Token Representations in Chat-Template Prompt Injection

    Sep 28, 2026Yan Zhan, Yunze Song, Mengkai Hou +3Instruction-Tuned ModelsPrompt Engineering

    Peking University · National University of Singapore · BYD Company Limited +1

  14. Faithful Activation Verbalization: Reducing Hallucinations in LLM Representation Interpretation

    Sep 27, 2026Haiyan Zhao, Zirui Hei, Wei Shi +3VerbalizationLarge Language Model Hallucination

    New Jersey Institute of Technology · Shanghai AI Laboratory · Xi’an JiaoTong University +1

  15. Lost with a Map: Conversational State and Behavioral Reliability in Language Models

    Sep 27, 2026Atahan Dokme, Larry HeckConversational ContextInstruction-Tuned Models

    Georgia Institute of Technology

  16. How code helps different tasks? A decompositional lens on LLM post-training

    Sep 27, 2026Zheng Yu, Yiwei Li, Yishen Chen +4Instruction-Tuned ModelsPost-Training

    Sun Yat-sen University · Shenzhen Loop Area Institute · The Chinese University of Hong Kong, Shenzhen +1

  17. ENDOPROMPT: Victim-Side Pseudo-References for Utility Degradation

    Sep 24, 2026Qingyu Wu, Zeyu Feng, Yongda Yu +2Prompt EngineeringInstruction-Tuned Models

    Defense Innovation Institute, Academy of Military Science, Beijing, China · Nanjing University, Nanjing, China

  18. Rewired or Gated? How Instruction Tuning Shapes Knowledge-Conflict Circuits in LLMs

    Sep 22, 2026Shubham Santosh Pandere, Gautam Ranka, Ritika Varshney +3Instruction TuningInstruction-Tuned Models

    IvLabs, VNIT

  19. Detecting Soft Errors in Parallel Software with LLM-tuned Instruction Duplication

    Sep 17, 2026Yafan Huang, Guanpeng LiReal-Tool BenchmarksInstruction-Tuned Models

    University of Iowa Iowa City, IA, USA · University of Florida Gainesville, FL, USA

  20. Larger Context Window, Fewer Overcorrections: Optimizing Prompts and Batching for Minimal-Edit Grammatical Error Correction

    Sep 11, 2026Kateryna Karpo, Artem ChernodubGrammatical Error CorrectionCorrection

    Ukrainian Catholic University · YouScan · Zendesk

  21. Compositional Multilingual and Behavioral Attribute Steering

    Sep 8, 2026Hyun Gu Kang, Daniil Gurgurov, Tanja Baeumel +2Linear Activation SteeringSteering

    1German Research Centre for Artificial Intelligence (DFKI) · 2Saarland University · Centre for European Research in Trusted AI (CERTAIN)

  22. Stabilizing Instruction Supervision for Instruct-TTS via Controllable Diversification and Drift Filtering

    Sep 8, 2026Yizhong Geng, Kecan Mao, Qifei Li +6Instruction TuningInstruction

    Beijing University of Posts and Telecommunications, China · Li Auto, China

  23. In-Place Instruction Following in Diffusion Language Models

    Sep 7, 2026Zheng Nie, Zherui Li, Jiaming Zhang +3Diffusion Language ModelsInstruction-Tuned Models

    National University of Singapore · Nanyang Technological University · Peking University

  24. ESPO: Error-Structured Prompt Optimization via Diagnose, Diversify, and Stabilize

    Sep 3, 2026Lihao Liu, Peng Tang, Kunwar Yashraj Singh +1Automatic Prompt OptimizationInstruction-Tuned Models

    AWS Agentic AI

  25. Instruction Duplication as an Inference-Time Control Primitive

    Sep 3, 2026Victor LavrenkoInstructionRepetition

    PeaceTech VC, Israel

  26. LLMs Learn Better In-Context from Rules than from Examples

    Sep 2, 2026Xiang Fu, Seungmin Cho, Yukyung Lee +1In-Context LearningIn-Context

    Boston University

  27. How Output Format Confounds Data Quality and Capability in Instruction Tuning

    Sep 2, 2026Chengguang Gan, Hanjun Wei, Yunhao Liang +3Instruction TuningData Quality

    1Independent Researcher · University of Chinese Academy of Sciences · 3Pusan National University +2

  28. Prompt-Robust Language Models: Which Training Strategies Work?

    Sep 1, 2026Frederic Sadrieh, Michal ŠtefánikInstruction-Tuned ModelsIn-Context Learning

    Center for Information and Language Processing, LMU Munich · R&D Centre for Large Language Models, National Institute of Informatics, Japan

  29. Asymmetries in Spontaneous and Instructed Deception

    Aug 31, 2026Josiah LuikhamDeceptionInstruction-Tuned Models

    Independent Researcher

  30. Are You Sure You're Sure? On the Impact of Instruction Tuning on Confidence and Lexical Diversity

    Aug 13, 2026Irina Proskurina, Mayank Kumar, Oyindolapo O. KomolafeInstruction TuningInstruction-Tuned Models

    Cohere Labs Community · Laboratoire Hubert Curien, UMR CNRS 5516, Saint-Étienne, France · School of Computer Science Engineering and Technology (SCSET), Bennett University, Greater Noida, India +1

  31. EnterpriseRAG: Benchmarking LLM Instruction Adherence and Robustness under Non-Ideal Enterprise Retrieval

    Aug 12, 2026Huiqi Miao, Xinbao Sun, Bo Wang +6Instruction-Tuned ModelsLarge Reasoning Models

    Jiutian Research, China Mobile, Beijing, China

  32. When Self-Consistency Backfires: Majority Vote Hurts the Majority of Hard Science Problems for Small LLMs

    Aug 11, 2026Utkarsh BahugunaSelf-ConsistencyMajority Voting

    Scaler School of Technology

  33. When Do Task Vectors Interfere? Mapping the Validity Boundaries of Weight-Space Composition

    Aug 10, 2026Chencheng Zhu, Xiaoyang Li, Taotao CaiWeight-SpaceTask-Level

    UNSW Sydney · University of Southern Queensland

  34. UNSPECIFIC: General Constraint Synthesis for Breaking Copy-and-Paste Shortcut in LLM Instruction Following

    Aug 10, 2026Jeet Sharma, Balpreet Kaur, Jeremiah Hong +2Instruction-Tuned ModelsInstruction

    University of Massachusetts, Amherst, USA

  35. Harmful Content Is Not Enough: Continuation Framing Moderates In-Context Emergent Misalignment

    Aug 8, 2026Peiyang Liu, Xi Wang, Ziqiang Cui +2Emergent MisalignmentHarmful Content

    National Engineering Research Center for Software Engineering, Peking University, Beijing, China · Peking University, Beijing, China · City University of Hong Kong, Hong Kong SAR, China +1

  36. Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve

    Aug 4, 2026Denys Pushkin, Albert Q. Jiang, Aryo Lotfi +2Chain-of-Thought ReasoningInstruction-Tuned Models

    EPFL · Apple · Mistral AI

  37. Inverted Detection and Control in Steering Vectors

    Aug 3, 2026Max Torop, Aria Masoomi, Jennifer DyVectorsInstruction-Tuned Models

    Northeastern University

  38. Instruction-Conditioned Exploration for Reinforcement Learning with Self-Distillation to an Unconditioned Policy

    Aug 3, 2026Jim Dilkes, Vahid Yazdanpanah, Sebastian SteinLarge Language Model Reinforcement LearningUnsupervised On-Policy Self-Distillation

    University of Southampton Southampton United Kingdom

  39. Instruction Stacking Collapse: A Benchmark and the Capability-Dependent Value of Prompt Compilation

    Jul 31, 2026Atul Anand, Sourav ChattarajInstruction-Tuned ModelsInstruction

  40. IFHierBench: Hierarchical Instruction Following for Large Language Models

    Jul 30, 2026Yuetian Mao, Chunyang ChenInstruction-Tuned ModelsInstruction

    Technical University of Munich

  41. Selecting Open-Weight Language Models for Zero-Shot Intent Classification: A Systematic Evaluation of 41 Models

    Jul 29, 2026Parishruthi Ganesh, Gerry Dozier, Cheryl SealsInstruction-Tuned ModelsNatural Language Datasets

    Department of Computer Science and Software Engineering Auburn University Auburn, Alabama, USA

  42. Steering Instruction Hierarchies at Inference Time

    Jul 28, 2026Siqi Zeng, Sewoong Lee, Han Zhao +1Instruction-Tuned ModelsSteering

    Siebel School of Computing and Data Science University of Illinois, Urbana-Champaign Urbana, IL 61801, USA

  43. Instruction-Tuned Models Locally Reuse Human Syntax More Than Humans Do

    Jul 28, 2026Zandi EberstadtInstruction-Tuned ModelsSyntactic Structure

    Department of Computer Science University of Oxford

  44. Instruction-Tuned Language Models Cannot Sample from Distributions They Can Describe

    Jul 28, 2026Chaemin Jang, Dongman Lee, Jihee KimInstruction-Tuned ModelsPersona Consistency

    School of Computing, KAIST · School of Business and Technology Management, KAIST

  45. Where Steering Signals Come From: Activation Source Selection in Activation Steering

    Jul 28, 2026Jiaran Ye, Lingxu Ran, Zijun Yao +5Linear Activation SteeringSteering

    1MOE Key Laboratory of Computational Linguistics, Peking University · Department of Computer Science and Technology, Tsinghua University · 6YiXin-AILab, YIXIN, Beijing, China +3

  46. MemChain: Learning Interpretable Memory Traces for Memory-Augmented LLM Agents

    Jul 27, 2026Yiwen Ma, Songjun Tu, Qichao Zhang +3Instruction-Tuned ModelsTraces

    Institute of Automation, Chinese Academy of Sciences · School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences +1

  47. IKS-Instruct: A 24,000-Example Multilingual Dataset for Teaching Language Models Indian Knowledge Systems

    Jul 25, 2026Shwetha Singaravelu, Gayathri Muruganantham, Lakshmi Rajendran +1Natural Language DatasetsInstruction

    Intrinsic Lab, Centre for Sensors, Instrumentation and Cyber-Physical System Engineering (Centre for SeNSE), Indian Institute of Technology Delhi, New Delhi 110016, India · RSL Quantum, FITT, IIT Delhi, New Delhi 110016, India

  48. Wrong Design Intent Is Worse Than Never Conditioning: A Derangement-Control Diagnosis of Header Conditioning in CAD Program Completion

    Jul 25, 2026Yang XiaoCorrectInstruction-Tuned Models

    Sichuan University

  49. A Unified Moral-Value Dataset for Instruction Tuning

    Jul 23, 2026Zhaohui Zeng, Florian MaiInstruction TuningMoral Reasoning

    1RWTH Aachen · University of Bonn · 3Lamarr Institute for Machine Learning and Artificial Intelligence

  50. OPIUM: Mitigating Steering Externalities and Over-Refusal via Dual Objective Latent Optimization

    Jul 22, 2026Kavin Aravindan, Arihant Rastogi, Krishak Aneja +4Linear Activation SteeringModel Activations

    IIIT Hyderabad, India.

  51. Task Competence Is Not Instruction Following: Evaluating Instruction-Conflicting Behavior in Small Language Models

    Jul 21, 2026Mahdiyeh Farajidizaji, Vatsal RainaInstruction-Tuned ModelsInstruction

    Khajeh Nasir Toosi University of Technology · Apta AI, Spark AI Research

  52. Prompt Design at Scale: How Format, Instruction Count, and Context Length Shape Instruction Adherence and Hallucination in Large Language Models

    Jul 21, 2026Netanel EliavInstruction-Tuned ModelsPrecision Recall

    Machine Human Intelligence Lab (MHIL)

  53. CASE: Causal Alignment and Structural Enforcement for Improving Chain-of-Thought Faithfulness

    Jul 21, 2026Ziming Wang, Yinghua Yao, Changwu Huang +2Reasoning ChainInstruction-Tuned Models

    Department of Computer Science and Engineering of Southern University of Science and Technology, Shenzhen, China · Center for Frontier AI Research, Agency for Science, Technology and Research (A*STAR), Singapore · School of AI and Liberal Arts, Beijing Normal-Hong Kong Baptist University, Zhuhai, China +1

  54. Diagnosing Correctness Probes under Self-Judgement Confounding

    Jul 18, 2026Yi-Long LuCorrectnessInstruction-Tuned Models

    Key Laboratory of Adolescent Cyberpsychology and Behavior (CCNU), Ministry of Education, Wuhan 430079, China · Key Laboratory of Human Development and Mental Health of Hubei Province, School of Psychology, Central China Normal University, Wuhan 430079, China

  55. PANOPTICON: A PII-Based Assemblage of Naturalistic Output Tokens for Investigating Privacy Leakage Within LLM Context Window

    Jul 17, 2026Ryan Thornton, Mir Mehedi Ahsan Pritom, Maanak GuptaPrivacyAttacker Large Language Model

    Department of Computer Science Tennessee Tech University Cookeville, TN, USA

  56. Leveraging Instruction Tuning and Merging for Reasoning Model Adaptation

    Jul 16, 2026Yu-Du Feng, Niels Mündler-Sasahara, Mark Vero +1LLM Reasoning StrategiesInstruction Tuning

    Department of Computer Science, ETH Zurich, Zurich, Switzerland.

  57. Extending LLM Context via Associative Recurrent Memory

    Jul 13, 2026Gleb Kuzmin, Ivan Rodkin, Aydar Bulatov +8Efficient Long-Context InferenceInstruction-Tuned Models

    1FusionBrain Lab 2MBZUAI 3Cognitive AI Systems Lab 4RUDN · 2MBZUAI · 6MIRAI +5

  58. From Direction to Magnitude: How Multimodal Instruction-Tuning Reorganizes the Geometric Encoding of Identity-Specifying Prompts in Transformer Hidden States

    Jul 10, 2026Jorge A. Castillo, Marco Torres Yévenes, Juan Carlos LanasMultimodal Continual Instruction TuningInstruction-Tuned Models

    Axis Dynamics SpA, Santiago, Chile

  59. Two Axes of LLM Abstention: Answer Correctness and Question Answerability

    Jul 9, 2026Benedikt J. WagnerAnswerInstruction-Tuned Models

    City St George’s, University of London

  60. Prompt Compression via Activation Aggregation

    Jul 9, 2026Thibaud Ardoin, Semira Einsele, Evis Bregu +1Large Language Model CompressionInstruction-Tuned Models

    Freie Universität Berlin