This episode examines PASTA, a method that lets users highlight part of a prompt and has the model attend to it more strongly, without changing any weights. It covers why markup like asterisks may not work as emphasis for LLMs. It then places PASTA against instruction tuning, activation steering (ActAdd, CAA, Inference-Time Intervention) and knowledge editing (ROME, MEMIT, REMEDI). The key difference is that PASTA changes where selected attention heads read, rather than what they output. The discussion explains the mechanism: scores outside the highlighted span are scaled by a small alpha (0.01) and renormalized, which is equivalent to a roughly hundredfold relative boost on the span. The hosts also raise questions about head selection and evaluation, including the absence of comparisons against the neighboring steering methods. Listeners interested in controllability, long-context failures and conflicts between a prompt and a model's memorized knowledge will find it useful.
Sources:
1. Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs — Qingru Zhang, Chandan Singh, Liyuan Liu, Xiaodong Liu, Bin Yu, Jianfeng Gao, Tuo Zhao, 2023
http://arxiv.org/abs/2311.02262
2. Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs — Qingru Zhang, Chandan Singh, Liyuan Liu, Xiaodong Liu, Bin Yu, Jianfeng Gao, Tuo Zhao, 2023 (arXiv 2311.02262); ICLR 2024
https://scholar.google.com/scholar?q=Tell+Your+Model+Where+to+Attend%3A+Post-hoc+Attention+Steering+for+LLMs
3. Prompt-to-Prompt Image Editing with Cross-Attention Control — Amir Hertz, Ron Mokady, Jay Tenenbaum, Kfir Aberman, Yael Pritch, Daniel Cohen-Or, 2022
https://scholar.google.com/scholar?q=Prompt-to-Prompt+Image+Editing+with+Cross-Attention+Control
4. Efficient Streaming Language Models with Attention Sinks — Guangxuan Xiao, Yuandong Tian, Beidi Chen, Song Han, Mike Lewis, 2023 (ICLR 2024)
https://scholar.google.com/scholar?q=Efficient+Streaming+Language+Models+with+Attention+Sinks
5. Lost in the Middle: How Language Models Use Long Contexts — Nelson F. Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, Percy Liang, 2023 (TACL 2024)
https://scholar.google.com/scholar?q=Lost+in+the+Middle%3A+How+Language+Models+Use+Long+Contexts
6. Inference-Time Intervention: Eliciting Truthful Answers from a Language Model — Kenneth Li, Oam Patel, Fernanda Viégas, Hanspeter Pfister, Martin Wattenberg, 2023 (NeurIPS 2023)
https://scholar.google.com/scholar?q=Inference-Time+Intervention%3A+Eliciting+Truthful+Answers+from+a+Language+Model
7. Steering Llama 2 via Contrastive Activation Addition — Nina Rimsky, Nick Gabrieli, Julian Schulz, Meg Tong, Evan Hubinger, Alexander Turner, 2023
https://scholar.google.com/scholar?q=Steering+Llama+2+via+Contrastive+Activation+Addition
8. Activation Addition: Steering Language Models Without Optimization — Alexander Matt Turner, Lisa Thiergart, David Udell, Gavin Leech, Ulisse Mini, Monte MacDiarmid, 2023
https://scholar.google.com/scholar?q=Activation+Addition%3A+Steering+Language+Models+Without+Optimization
9. Trusting Your Evidence: Hallucinate Less with Context-aware Decoding — Weijia Shi, Xiaochuang Han, Mike Lewis, Yulia Tsvetkov, Luke Zettlemoyer, Scott Wen-tau Yih, 2023
https://scholar.google.com/scholar?q=Trusting+Your+Evidence%3A+Hallucinate+Less+with+Context-aware+Decoding
10. Retrieval Head Mechanistically Explains Long-Context Factuality — Wenhao Wu, Yizhong Wang, Guangxuan Xiao, Hao Peng, Yao Fu, 2024
https://scholar.google.com/scholar?q=Retrieval+Head+Mechanistically+Explains+Long-Context+Factuality
11. Model Tells You Where to Merge / AutoPASTA: Model Tells You What to Discard (Adaptive KV cache compression) — Various (follow-up and adjacent work, see AutoPASTA by Zhuang et al. 2024), 2024
https://scholar.google.com/scholar?q=Model+Tells+You+Where+to+Merge+%2F+AutoPASTA%3A+Model+Tells+You+What+to+Discard+%28Adaptive+KV+cache+compression%29
12. Spotlight Your Instructions: Instruction-following with Dynamic Attention Steering (SPA) — Praveen Venkateswaran, Danish Contractor, 2025
https://scholar.google.com/scholar?q=Spotlight+Your+Instructions%3A+Instruction-following+with+Dynamic+Attention+Steering+%28SPA%29
13. FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning — Tri Dao, 2023
https://scholar.google.com/scholar?q=FlashAttention-2%3A+Faster+Attention+with+Better+Parallelism+and+Work+Partitioning
14. Attention is not Explanation / Attention is not not Explanation — Sarthak Jain and Byron Wallace; Sarah Wiegreffe and Yuval Pinter, 2019
https://scholar.google.com/scholar?q=Attention+is+not+Explanation+%2F+Attention+is+not+not+Explanation
15. Are Sixteen Heads Really Better than One? / Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting — Paul Michel, Omer Levy, Graham Neubig; Elena Voita et al., 2019
https://scholar.google.com/scholar?q=Are+Sixteen+Heads+Really+Better+than+One%3F+%2F+Analyzing+Multi-Head+Self-Attention%3A+Specialized+Heads+Do+the+Heavy+Lifting
Interactive Visualization: PASTA: Steering LLM Attention Toward Highlighted Prompt Text
