Can LLMs Separate Pasted Artifacts from User Speech? Absorption at Unmarked Prompt Seams
cs.CL
Submitted: 2026-10-03
Updated: 2026-10-03
Code: https://github.com/aimsresearchlab/seam
Sources
- Get my drift? Catching LLM Task Drift with Activation Deltas
- Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructions
- The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence
- StruQ: Defending Against Prompt Injection with Structured Queries
- SecAlign: Defending Against Prompt Injection with Preference Optimization
- AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
- Defeating Prompt Injections by Design
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- The Announcement Carries the Cue: Markup, Boundaries, and the Notation of Pre-Training Corpora
- Gemma 3 Technical Report
- The Llama 3 Herd of Models
- Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
- DeBERTa: Decoding-enhanced BERT with Disentangled Attention
- Defending Against Indirect Prompt Injection Attacks With Spotlighting
- LLMs can be easily Confused by Instructional Distractions
- MiniMax Sparse Attention
- Formalizing and Benchmarking Prompt Injection Attacks and Defenses
- DataSentinel: A Game-Theoretic Detection of Prompt Injection Attacks
- OctoPack: Instruction Tuning Code Large Language Models
- gpt-oss-120b & gpt-oss-20b Model Card
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering