CLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoning
CLaRa is a unified RAG framework that compresses documents into continuous vectors and jointly optimizes the reranker and generator via end-to-end training. It introduces SCP for key-preserving data synthesis and uses a differentiable top-k estimator, achieving state-of-the-art compression and reranking at 16x compression rates.
content type paperpublished July 2026
CLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoning
AuthorsJie He†**, Richard He Bai, Sinead Williamson, Jeff Z. Pan†, Navdeep Jaitly, Yizhe Zhang
View publication
Retrieval-augmented generation (RAG) enhances large language models (LLMs) with external knowledge but still suffers from long contexts and disjoint retrieval–generation optimization. In this work, we propose CLaRa (Continuous Latent Reasoning), a unified framework that performs embedding-based compression and joint optimization in a shared continuous space. To obtain semantically rich and retrievable compressed vectors, thereby reducing the document length fed into the generator, we introduce SCP, a key-preserving data synthesis framework based on question-answering and paraphrase supervision. CLaRa then trains the reranker and generator end-to-end via a single language modeling loss, with gradients flowing through both modules using a differentiable top-k estimator. Theoretically, this unified optimization aligns retrieval relevance with answer quality. Experiments across multiple QA benchmarks show that CLaRa achieves state-of-the-art compression and reranking performance, even at a text compression rate of 16, outperforming text-based fine-tuned baselines.
† University of Edinburgh
** Work done while at Apple
Compress and Compare: Interactively Evaluating Efficiency and Behavior Across ML Model Compression Experiments
September 27, 2024research area Human-Computer Interaction, research area Tools, Platforms, Frameworksconference IEEE Visualization
*Equal Contributors
To deploy machine learning models on-device, practitioners use compression algorithms to shrink and speed up models while maintaining their high-quality output. A critical aspect of compression in practice is model comparison, including tracking many compression experiments, identifying subtle changes in model behavior, and negotiating complex accuracy-efficiency trade-offs. However, existing compression tools poorly support…
Read more
Context Tuning for Retrieval Augmented Generation
December 18, 2023research area Knowledge Bases and Search, research area Speech and Natural Language ProcessingWorkshop at EACL
This paper was accepted at the UncertaiNLP workshop at EACL 2024.
Large language models (LLMs) have the remarkable ability to solve new tasks with just a few examples, but they need access to the right tools. Retrieval Augmented Generation (RAG) addresses this problem by retrieving a list of relevant tools for a given task. However, RAG’s tool retrieval step requires all the required information to be explicitly present in the query. This is a…
Read more