Instruction Tuning

Follow this topic Ask about this topic

Recent momentum

-40%

3 papers in the last 28 days · 0.1% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-14

1 new paper

A weekly snapshot of new work published in Instruction Tuning.

Period ending 2026-09-07

2 new papers

A weekly snapshot of new work published in Instruction Tuning.

47 papers

Latest in Instruction Tuning

Open your feed →

Stabilizing Instruction Supervision for Instruct-TTS via Controllable Diversification and Drift Filtering
Sep 8, 2026Yizhong Geng, Kecan Mao, Qifei Li +6Instruction Tuning Instruction
LLMs Learn Better In-Context from Rules than from Examples
Sep 2, 2026Xiang Fu, Seungmin Cho, Yukyung Lee +1In-Context Learning In-Context
How Output Format Confounds Data Quality and Capability in Instruction Tuning
Sep 2, 2026Chengguang Gan, Hanjun Wei, Yunhao Liang +3Instruction Tuning Data Quality
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 Tuning Instruction-Tuned Large Language Models
Is Convergence Inevitable? Tracing Output Homogeneity Back to Base Models
Aug 11, 2026Alexandrine Fortier, Hazel Chen, Peter WestSemantic Consistency Instruction Tuning
DistMoE: Private-data Rehearsal-free Routing in Mixture-of-Experts for Distributed Instruction Tuning
Aug 10, 2026Mainak Singha, Niccolò Biondi, Elisa Ricci +1Multimodal Instruction Tuning Instruction Tuning
Where Steering Signals Come From: Activation Source Selection in Activation Steering
Jul 28, 2026Jiaran Ye, Lingxu Ran, Zijun Yao +5Linear Activation Steering Steering
A Unified Moral-Value Dataset for Instruction Tuning
Jul 23, 2026Zhaohui Zeng, Florian MaiInstruction Tuning Moral Reasoning
Learning from Synthetic Data without Model Collapse in Iterative Instruction Tuning
Jul 19, 2026Xiaonan Luo, Yue Huang, Kehan Guo +4Instruction Tuning Synthetic Training Data
Leveraging Instruction Tuning and Merging for Reasoning Model Adaptation
Jul 16, 2026Yu-Du Feng, Niels Mündler-Sasahara, Mark Vero +1LLM Reasoning Methods Instruction Tuning
Unlocking Speech-Text Compositional Powers: Instruction-Following Speech Language Models without Instruction Tuning
Jul 2, 2026Congrui Du, Yang Zhang, Kaizhi Qian +1Speech Language Models Large Audio Language Models
Online Data Selection for Instruction Tuning via Gaussian Processes
Jun 29, 2026Jun Wang, Quoc Phong Nguyen, Julien Monteil +1Instruction Tuning Instruction-Tuned Large Language Models
TraMP-LLaMA: Generative Interpretability with Decoupled Instruction Tuning for Facial Expression Quality Assessment
Jun 25, 2026Shuchao Duan, Alan Whone, Hossein Rahmani +2Facial Expression Recognition Multimodal Evaluation
Aligning MusicLLM with Emotion using Instruction Tuning and Feedback-Driven Alignment
Jun 23, 2026Takuya Hasumi, Welly NaptaliMusic Understanding Instruction Tuning
LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling
Jun 16, 2026Jian Yang, Shawn Guo, Wei Zhang +16Loop Test-Time Scaling
VoidPadding: Let [VOID] Handle Padding in Masked Diffusion Language Models so that [EOS] Can Focus on Semantic Termination
Jun 16, 2026Chunyu Liu, Zhengyang Fan, Kaisen Yang +1Masked Diffusion Language Models Instruction Tuning
From Tokens to Regions: CUDA-Sensitive Instruction Tuning for GPU Kernel Generation
Jun 15, 2026Wentao Chen, Jiace Zhu, Xing Zhe Chai +4Graphics Processing Unit Kernels Instruction Tuning
A Low-Rank Subspace Analysis of LLM Interventions
Jun 12, 2026Angira Sharma, Christian Schroeder de Witt, Philip Torr +2AI Behavior Analysis Causal Intervention
Steering Where to Listen: Instruction-Based Activation Steering Redirects Temporal Attention in Large Audio-Language Models
Jun 9, 2026Tsung-En Lin, Hung-Yi LeeLarge Audio Language Models Activation Steering
Lost in the Flow with Code Talkers: Unveiling the Instruction-Tuning Tax of Large Language Models in Code Tasks
Jun 7, 2026Shi Ying Chang, Chiok Yew Ho, Yichen Li +1Instruction Tuning AI Code Generation
Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness
Jun 4, 2026Victor De Marez, Luna De Bruyne, Walter DaelemansSycophancy Instruction Tuning
Visual Instruction Tuning Aligns Modalities through Abstraction
Jun 2, 2026Luis Palacios, Lorenzo Basile, Diego Doimo +1Multimodal Instruction Tuning Vision-Language Reasoning
Large Language Models Are Overconfident in Their Own Responses
Jun 2, 2026Mario Sanz-Guerrero, Manuel Mager, Katharina von der WenseOverconfidence Instruction Tuning
ProtoAda: Prototype-Guided Adaptive Adapter Expansion and Geometric Consolidation for Multimodal Continual Instruction Tuning
Jun 1, 2026Yu-Cheng Shi, Zhen-Hao Xie, Jun-Tao Tang +1Multimodal Instruction Tuning Vision-Language Model Adaptation
CRAM: Centroid-Routing and Adaptive MoE for Multimodal Continual Instruction Tuning
Jun 1, 2026Jun-Tao Tang, Zhen-Hao Xie, Yu-Cheng Shi +1Multimodal Instruction Tuning Instruction Tuning
Decentralized Instruction Tuning: Conflict-Aware Splitting and Weight Merging
Jun 1, 2026Minsik Choi, Geewook KimInstruction Tuning Split Learning
MADS: Model-Aware Diverse Core Set Selection for Instruction Tuning
May 29, 2026Yi Bai, Wenhao Zhang, Yao Chen +3Instruction Tuning Large Language Model Fine-Tuning
Beyond Bilingual Transfer: Multilingual Code-Switching in Instruction Tuning
May 28, 2026Shunta Asano, Jeonghun Baek, Toshihiko YamasakiCross-Lingual Transfer Multilingual
Prism: A Plug-in Reproducible Infrastructure for Scalable Multimodal Continual Instruction Tuning
May 25, 2026Jun-Tao Tang, Yu-Cheng Shi, Zhen-Hao Xie +1Multimodal Instruction Tuning Instruction Tuning
BeLink: Biomedical Entity Linking Meets Generative Re-Ranking
May 21, 2026Darya Shlyk, Stefano Montanelli, Lawrence HunterBiomedical Entity Cross-Encoder Reranker
DarkLLM: Learning Language-Driven Adversarial Attacks with Large Language Models
May 15, 2026Ye Sun, Xin Wang, Jiaming Zhang +7Black-Box Adversarial Attacks Multimodal Foundation Model
Targeted Neuron Modulation via Contrastive Pair Search
May 12, 2026Sam Herring, Jake Naviasky, Karan MalhotraLinear Activation Steering Instruction Tuning
A Unified Graph Language Model for Multi-Domain Multi-Task Graph Alignment Instruction Tuning
May 12, 2026Haibo Chen, Xin Wang, Jiaheng Chao +2Large Language Model Alignment Gnn-Based Detectors
Dynamic Cross-Modal Prompt Generation for Multimodal Continual Instruction Tuning
May 11, 2026Tao Hu, Da-Wei ZhouMultimodal Instruction Tuning Instruction Tuning
Instruction Tuning Changes How Upstream State Conditions Late Readout: A Cross-Patching Diagnostic
May 8, 2026Yifan ZhouInstruction Tuning Model Activations
The Convergence Gap: Instruction-Tuned Language Models Stabilize Later in the Forward Pass
May 8, 2026Yifan ZhouInstruction Tuning Intermediate Checkpoints
Open-Source Image Editing Models Are Zero-Shot Vision Learners
May 6, 2026Wei Liu, Jiaxin Lin, Rui ChenImage Editing Depth Estimation
GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models
May 2, 2026Zhiwen Ruan, Yichao Du, Jianjie Zheng +6Instruction Tuning Instruction
Attention Is Where You Attack
Apr 30, 2026Aviral Srivastava, Sourav PandaBlack-Box Adversarial Attacks Jailbreaks
What Makes Good Instruction-Tuning Data? An In-Context Learning Perspective
Apr 28, 2026Guangzeng Han, Xiaolei HuangInstruction Tuning Efficient Data Selection
Efficient Low-Resource Language Adaptation via Multi-Source Dynamic Logit Fusion
Apr 20, 2026Chen Zhang, Jiuheng Lin, Zhiyuan Liao +1Large Language Model Adaptation Logit Lens
Where Does Robustness Live? Neuron-Guided Adaptation for Retrieval-Augmented Language Models
Apr 2, 2026Jae O Lee, Jaemin Kim, Sumyeong Ahn +1Large Language Model Adaptation Instruction Tuning
VisNec: Measuring and Leveraging Visual Necessity for Multimodal Instruction Tuning
Mar 1, 2026Mingkang Dong, Hongyi Cai, Jie Li +4Multimodal Instruction Tuning Visual In-Context Learning
Patches of Nonlinearity: Instruction Vectors in Large Language Models
Feb 8, 2026Irina Bigoulaeva, Jonas Rohweder, Subhabrata Dutta +1Instruction Tuning Instruction-Tuned Large Language Models
SecureCode: A Production-Grade Multi-Turn Dataset for Training Security-Aware Code Generation Models
Dec 20, 2025Scott ThorntonSecurity Analysis Vulnerable Code
DynamixSFT: Dynamic Mixture Optimization of Instruction Tuning Collections
Aug 16, 2025Haebin Shin, Lei Ji, Xiao Liu +4Multimodal Instruction Tuning Instruction Tuning
How LLMs Follow Instructions: Skillful Coordination, Not a Universal Mechanism
Date pendingElisabetta Rocchetti, Alfio FerraraInstruction Tuning Instruction

Sep 8, 2026 · cs.SDJ/K move · Enter open · S save

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

Yizhong Geng, Kecan Mao, Qifei Li, Cong Wang+5

Instruct-TTS systems expand structured style labels into natural-language training instructions through LLM rewriting, yet we find that over 40% of unconstrained rewrites contain semantic drift that corrupts supervision and weakens generalization. We formalize this problem as instruction supervision instability and propose a data-centric stabilization recipe that jointly improves coverage and fidelity through three mechanisms: controllable instruction diversification for systematic expansion, LLM-based drift filtering for quality control, and attribute-aligned supervision that grounds prosody control in acoustic perturbations. On the Chinese split of InstructTTSEval, our recipe raises instruction-following from 34.5% without fine-tuning and 51.0% with naive fine-tuning to 56.4%, while constrained rewriting reduces drift from 40.4% to 15.4%. Ablations confirm the three mechanisms are complementary, and the drift taxonomy may generalize to instruction-driven generation beyond TTS.

Instruction Tuning Instruction Instruction-Tuned Large Language Models Prosody Output and Model Diversity

Open paper Ask about it PDF