SAGE: Safe, Adaptive Generation Engine for Long Form Document Generation in Collaborative, High Stakes Domains
Abrar Rahman, Anish Sundar · Team Benki
Submitted to Reprogramming AI Models Hackathon. Sprint projects are early-stage work by participants, not Apart Research publications.
Long-form document generation for high-stakes financial services—such as deal memos, IPO prospectuses, and compliance filings—requires synthesizing data-driven accuracy, strategic narrative, and collaborative feedback from diverse stakeholders. While large language models (LLMs) excel at short-form content, generating coherent long-form documents with multiple stakeholders remains a critical challenge, particularly in regulated industries due to their lack of interpretability.
We present SAGE (Secure Agentic Generative Editor), a framework for drafting, iterating, and achieving multi-party consensus for long-form documents. SAGE introduces three key innovations: (1) a tree-structured document representation with multi-agent control flow, (2) sparse autoencoder-based explainable feedback to maintain cross-document consistency, and (3) a version control mechanism that tracks document evolution and stakeholder contributions.
Reviews
This is a really well-presented work that presents a framework/tooling to improve long-form document generation. In future, it would be interesting to see a benchmark on document quality whether steering the LLM towards a specific thing (e.g. to be more technical) deteriorates quality in other ways.
Feels off topic, potentially trying to advertise for a company called Benki
Not related to AI Safety. I do not understand if this is mostly to promote the Benki finance company
My impression is that you implemented SAE features in your long-context document editing tool and I think this seems pretty awesome. When it comes to your node-based document iteration engine and its evaluation suite, this also seems very valuable and is probably more relevant when it comes to safety than the features used for content development.
You link to the blog posts and I agree that the verification of content in financial documents is very important, though I’ll mention that your submission probably doesn’t score maximum on methodology due to the lack of experiments to validate your method. The safety arguments also aren’t super strong and the submitted project is somewhat adjacent to the topic of the hackathon, though your product seems relevant to ensure accuracy in financial documents.
In terms of directing your work towards safety, I suggest you take existing documents and discover errors using various feature-supported evaluators to improve the project (e.g. going for some of the public pitch decks might be a good example). If you can prove that, it’s simply rock’n’roll and I can see some use cases beyond finance as well (though it’s a great place to start a company).
Read full reviewShow less
This is exciting, if incomplete work. I agree with Esben in regards to specific methodologies that could unlock further evidence for the success rate of this node-based model. Come back to us when you have revenue :)
Cite this project
@misc{rahman2024sage,
title = {{SAGE: Safe, Adaptive Generation Engine for Long Form Document Generation in Collaborative, High Stakes Domains}},
author = {Abrar Rahman and Anish Sundar},
year = {2024},
month = nov,
note = {Submitted to Reprogramming AI Models Hackathon, an Apart Research Sprint},
howpublished = {\url{https://apartresearch.com/sprints/projects/sage-safe-adaptive-generation-engine-for-long-form-document-generation-in-collaborative-high-stakes-domains}},
url = {https://apartresearch.com/sprints/projects/sage-safe-adaptive-generation-engine-for-long-form-document-generation-in-collaborative-high-stakes-domains}
}More from Reprogramming AI Models Hackathon
- 1st place by peer reviewView project: AutoSteer: Weight-Preserving Reinforcement Learning for Interpretable Model Control
AutoSteer: Weight-Preserving Reinforcement Learning for Interpretable Model Control
AI Safety Initiative Groningen
Traditional fine-tuning methods for language models, while effective, often disrupt internal model features that could provide valuable insights into model behavior. We present a novel approach combining Reinforcement …
- View project: Classification on Latent Feature Activation for Detecting Adversarial Prompt Vulnerabilities
Classification on Latent Feature Activation for Detecting Adversarial Prompt Vulnerabilities
Feature Disruption Lab
We present a method leveraging Sparse Autoencoder (SAE)-derived feature activations to identify and mitigate adversarial prompt hijacking in large language models (LLMs). By training a logistic regression classifier on …
- View project: Utilitarian Decision-Making in Models - Evaluation and Steering
Utilitarian Decision-Making in Models - Evaluation and Steering
Byte To Brain
We design an eval based on the Oxford Utilitarianism Scale (OUS) that measures the model’s deontological vs utilitarian preference in a nine question, two factor model. Using this scale, we measure how feature steering …