Instruction-Tuned Models

Follow this topic Ask about this topic

Recent momentum

-22%

14 papers in the last 28 days · 0.2% 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 2026-09-21

3 new papers

A weekly snapshot of new work published in Instruction-Tuned Models.

Period ending 2026-09-14

2 new papers

A weekly snapshot of new work published in Instruction-Tuned Models.

Period ending 2026-09-07

6 new papers

A weekly snapshot of new work published in Instruction-Tuned Models.

148 papers

Latest in Instruction-Tuned Models

Browse all topics →

Steer Like the LLM: Activation Steering that Mimics Prompting
May 5, 2026Geert Heyman, Frederik VandeputteActivation Steering Instruction-Tuned Models
Geometric Deviation as an Unsupervised Pre-Generation Reliability Signal: Probing LLM Representations for Answerability
May 4, 2026Yucheng DuInstruction-Tuned Models
Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels
May 2, 2026Plawan Kumar Rath, Rahul MaliakkalLarge Language Model Quantization Quantization
GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models
May 2, 2026Zhiwen Ruan, Yichao Du, Jianjie Zheng +6Finetuning Instruction-Tuned Models
A Systematic Post-Train Framework for Video Generation
Apr 28, 2026Zeyue Xue, Siming Fu, Jie Huang +9Pre-Trained Video Diffusion Models LLM Post-Training Methods
What Makes Good Instruction-Tuning Data? An In-Context Learning Perspective
Apr 28, 2026Guangzeng Han, Xiaolei HuangInstruction Tuning Multimodal Instruction Tuning
Distilling Self-Consistency into Verbal Confidence: A Pre-Registered Negative Result and Post-Hoc Rescue on Gemma 3 4B
Apr 27, 2026Jon-Paul CacioliSelf-Consistency Instruction-Tuned Models
Small Language Model Helps Resolve Semantic Ambiguity of LLM Prompt
Apr 25, 2026Zhenzhen Huang, Chaoning Zhang, Fachrina Dewi Puspitasari +4Large Language Model Reasoning Prior Prompt Optimization Techniques
Cross-Dataset Bloom Question Classification: Supervised Models and Prompted LLMs
Apr 22, 2026Abdolali Faraji, Mohammadreza Molavi, Zohreh Rasoulkhani +2Computerized Adaptive Testing Education
To Intervene or Not: Guiding Inference-time Alignment with Probabilistic Model Blending
Apr 22, 2026Jin Gan, Xin Li, Jun LuoLarge Language Model Alignment Instruction-Tuned Models
Harmful Intent as a Geometrically Recoverable Feature of LLM Residual Streams
Apr 20, 2026Isaac Llorente-SaguerLarge Language Model Safety Instruction-Tuned Models
Generalization Boundaries of Fine-Tuned Small Language Models for Graph Structural Inference
Apr 20, 2026Michal PodstawskiGraph Representation Learning Large Language Model Fine-Tuning
From Craft to Kernel: A Governance-First Execution Architecture and Semantic ISA for Agentic Computers
Apr 20, 2026Xiangyu Wen, Yuang Zhao, Xiaoyu Xu +9Agentic Systems Runtime Enforcement
TinyJudge: Unverifiable Constraint Alignment via Lightweight Specialist Ensembles
Apr 19, 2026Yirong Zeng, Yufei Liu, Xiao Ding +9Instruction-Tuned Models Raw Judge Outputs
Safety Training Modulates Harmful Misalignment Under On-Policy RL, But Direction Depends on Environment Design
Apr 14, 2026Leon Eshuijs, Shihan Wang, Antske FokkensSafety Alignment Safety
PROMPT2BOX: Uncovering Entailment Structure among LLM Prompts
Mar 22, 2026Neeladri Bhuiya, Shib Sankar Dasgupta, Andrew McCallum +1Instruction-Tuned Models Prompt Engineering
Effective Distillation to Hybrid xLSTM Architectures
Mar 16, 2026Lukas Hauzenberger, Niklas Schmidinger, Thomas Schmied +7Instruction-Tuned Models Bidirectional Long Short-Term Memory
From Refusal Tokens to Refusal Control: Discovering and Steering Category-Specific Refusal Directions
Mar 9, 2026Rishab Alagharu, Ishneet Sukhvinder Singh, Shaibi Shamsudeen +2Refusals Large Language Model Safety
Patches of Nonlinearity: Instruction Vectors in Large Language Models
Feb 8, 2026Irina Bigoulaeva, Jonas Rohweder, Subhabrata Dutta +1Instruction-Tuned Models Model Activations
AP-BMM: Approximating Capability-Cost Pareto Sets of LLMs via Asynchronous Prior-Guided Bayesian Model Merging
Dec 10, 2025Kesheng Chen, Yamin Hu, Zhenqian Zhu +2Continual Model Merging Large Language Model Serving
Reasoning Up the Instruction Ladder for Controllable Language Models
Oct 30, 2025Zishuo Zheng, Vidhisha Balachandran, Chan Young Park +2Instruction-Tuned Models Ladder
LuxIT: A Luxembourgish Instruction Tuning Dataset from Monolingual Seed Data
Oct 28, 2025Julian Valline, Cedric Lothritz, Siwen Guo +1Multimodal Instruction Tuning Instruction-Tuned Models
TIIF-Bench: How Does Your T2I Model Follow Your Instructions?
Jun 2, 2025Xinyu Wei, Jinrui Zhang, Zeqing Wang +4Text-To-Image Evaluation Benchmarks
Man Made Language Models? Evaluating LLMs' Perpetuation of Masculine Generics Bias
Feb 14, 2025Enzo Doyen, Amalia TodirascuLarge Language Model Bias Gender
Hey, That's My Model! Introducing Chain & Hash, An LLM Fingerprinting Technique
Jul 15, 2024Mark Russinovich, Yanan Cai, Ahmed SalemFingerprint Instruction-Tuned Models
Measuring Pragmatic Influence in Large Language Model Instructions
Date pendingYilin Geng, Omri Abend, Eduard Hovy +1Task Framing Instruction-Tuned Models
How LLMs Follow Instructions: Skillful Coordination, Not a Universal Mechanism
Date pendingElisabetta Rocchetti, Alfio FerraraInstruction Instruction-Tuned Models
On The Effectiveness-Fluency Trade-Off In LLM Conditioning: A Systematic Study
Date pendingIuri Macocco, Pau Rodríguez, Arno Blaas +3Instruction-Tuned Models Fluency

May 5, 2026 · cs.CLJ/K move · Enter open · S save

Steer Like the LLM: Activation Steering that Mimics Prompting

Geert Heyman, Frederik Vandeputte

Nokia Bell Labs, Belgium.

Large language models can be steered at inference time through prompting or activation interventions, but activation steering methods often underperform compared to prompt-based approaches. We propose a framework that formulates prompt steering as a form of activation steering and investigates whether distilling successful prompt steering behavior into simpler, interpretable models can close this gap. Our analysis reveals that popular activation steering methods are not faithful to the mechanics of prompt steering, which applies strong interventions on some tokens while barely affecting others. Based on these insights, we introduce Prompt Steering Replacement (PSR) models that estimate token-specific steering coefficients from the activations themselves and are trained to imitate prompt-based interventions. Experiments on three steering benchmarks across multiple language models show that PSR models outperform existing activation steering methods, especially when controlling for high-coherence completions, and also compare favorably to prompting on AxBench and persona steering.

Activation Steering Instruction-Tuned Models Steering Mimic

Open paper Ask about it PDF