# Doc2LoRA Provides Decodable Representations of Scientific Ideas

arXiv: https://arxiv.org/abs/2609.38374 · HTML: https://mlsanity.com/paper/2609.38374/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 64 of its 80 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Builds on (most cited first, 30 of 64)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [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)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [Perceiver: General Perception with Iterative Attention](https://mlsanity.com/paper/2103.03206/) (2021)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [TIES-Merging: Resolving Interference When Merging Models](https://mlsanity.com/paper/2306.01708/) (2023)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [Automatic chemical design using a data-driven continuous representation of molecules](https://mlsanity.com/paper/1610.02415/) (2016)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [Linear Mode Connectivity and the Lottery Ticket Hypothesis](https://mlsanity.com/paper/1912.05671/) (2019)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs](https://mlsanity.com/paper/1802.10026/) (2018)
- [Git Re-Basin: Merging Models modulo Permutation Symmetries](https://mlsanity.com/paper/2209.04836/) (2022)
- [SPECTER: Document-level Representation Learning using Citation-informed Transformers](https://mlsanity.com/paper/2004.07180/) (2020)
- [Learning to Compress Prompts with Gist Tokens](https://mlsanity.com/paper/2304.08467/) (2023)
- [LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition](https://mlsanity.com/paper/2307.13269/) (2023)
- [Adapting Language Models to Compress Contexts](https://mlsanity.com/paper/2305.14788/) (2023)
- [One Embedder, Any Task: Instruction-Finetuned Text Embeddings](https://mlsanity.com/paper/2212.09741/) (2022)
- [Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategies](https://mlsanity.com/paper/1804.11283/) (2018)
- [The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks](https://mlsanity.com/paper/2110.06296/) (2021)
- [LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models](https://mlsanity.com/paper/2310.05736/) (2023)
- [Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks](https://mlsanity.com/paper/2106.04489/) (2021)
- [SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer](https://mlsanity.com/paper/2110.07904/) (2021)
- [Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models](https://mlsanity.com/paper/2401.06102/) (2024)

## Abstract (arXiv)

Representing scientific papers as points in a space lets us search for similar papers and inquire about how fields relate to one another and drive innovation. Beyond search, the vector space of papers invites generation: mixing papers through simple vector operations creates new points, mirroring combinatorial novelty, the recombination of existing ideas into new ones. However, a mixed point often represents an idea no paper has yet realized, with no papers nearby to identify the idea. We propose representing each paper by a LoRA adapter generated by the Doc-to-LoRA hypernetwork. Every point in the space, including mixtures, thus represents a large language model (LLM) open to questions and instructions in natural language. On papers from the American Physical Society (APS), we instruct the LLM at the average of each subfield to name the field in a few words and obtain labels closer to the official names than the labels of five baselines, as judged by word overlap and a panel of five LLM judges. We also ask the LLMs at points between two APS papers to write an abstract and obtain descriptions shifting from one paper to the other in step with the mixing weight. While Doc-to-LoRA is trained for generation, a small invertible transform makes the embeddings competitive for search, on par with SPECTER2 and EmbeddingGemma and close to SBERT. Because the transform is invertible, every point in the transformed space still maps back to an LLM. The embeddings thus serve both search and generation, enabling researchers to question the idea at any point in the space as a starting point for generating new ideas.