# Eliciting Textual Descriptions from Representations of Continuous Prompts

arXiv: https://arxiv.org/abs/2410.11660 · HTML: https://mlsanity.com/paper/2410.11660/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 35 references that are in the map.
- First posted on arXiv 15 Oct 2024.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [Toy Models of Superposition](https://mlsanity.com/paper/2209.10652/) (2022)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://mlsanity.com/paper/1804.06876/) (2018)
- [Eliciting Latent Predictions from Transformers with the Tuned Lens](https://mlsanity.com/paper/2303.08112/) (2023)
- [Do Prompt-Based Models Really Understand the Meaning of their Prompts?](https://mlsanity.com/paper/2109.01247/) (2021)
- [State of What Art? A Call for Multi-Prompt LLM Evaluation](https://mlsanity.com/paper/2401.00595/) (2023)
- [Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models](https://mlsanity.com/paper/2401.06102/) (2024)
- [Text Embeddings Reveal (Almost) As Much As Text](https://mlsanity.com/paper/2310.06816/) (2023)
- [Future Lens: Anticipating Subsequent Tokens from a Single Hidden State](https://mlsanity.com/paper/2311.04897/) (2023)
- [Prompt Waywardness: The Curious Case of Discretized Interpretation of Continuous Prompts](https://mlsanity.com/paper/2112.08348/) (2021)
- [Generating Data to Mitigate Spurious Correlations in Natural Language Inference Datasets](https://mlsanity.com/paper/2203.12942/) (2022)
- [InversionView: A General-Purpose Method for Reading Information from Neural Activations](https://mlsanity.com/paper/2405.17653/) (2024)
- [Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RL](https://mlsanity.com/paper/2407.14733/) (2024)

## Built on by (most cited first, 4 of 4)

- [Do Activation Verbalization Methods Convey Privileged Information?](https://mlsanity.com/paper/2509.13316/) (2025)
- [Indications of Belief-Guided Agency and Meta-Cognitive Monitoring in Large Language Models](https://mlsanity.com/paper/2602.02467/) (2026)
- [Learning to Translate from Soft to Hard LLM Prompts](https://mlsanity.com/paper/2605.27642/) (2026)
- [Not All Drift Is a Mechanism: Tracing Prompt Adaptation in LLMs](https://mlsanity.com/paper/2610.18412/) (2026)

## Abstract (arXiv)

Continuous prompts, or "soft prompts", are a widely-adopted parameter-efficient tuning strategy for large language models, but are often less favorable due to their opaque nature. Prior attempts to interpret continuous prompts relied on projecting individual prompt tokens onto the vocabulary space. However, this approach is problematic as performant prompts can yield arbitrary or contradictory text, and it interprets prompt tokens individually. In this work, we propose a new approach to interpret continuous prompts that elicits textual descriptions from their representations during model inference. Using a Patchscopes variant (Ghandeharioun et al., 2024) called InSPEcT over various tasks, we show our method often yields accurate task descriptions which become more faithful as task performance increases. Moreover, an elaborated version of InSPEcT reveals biased features in continuous prompts, whose presence correlates with biased model predictions. Providing an effective interpretability solution, InSPEcT can be leveraged to debug unwanted properties in continuous prompts and inform developers on ways to mitigate them.