5 papers
Cartridges at Scale: Training Modular KV Caches over Large Document Collections
Momchil Hardalov, Gonzalo Iglesias, Adrià de Gispert
Large Language Models can reason over long contexts, yet prefilling millions of tokens is wasteful as much of the content remains static across queries. Cartridges address this by…
DeepFact: Co-Evolving Benchmarks and Agents for Deep Research Factuality
Yukun Huang, Leonardo F. R. Ribeiro, Momchil Hardalov +3
Search-augmented LLM agents can produce deep research reports (DRRs), but verifying claim-level factuality remains challenging. Existing fact-checkers are primarily designed for ge…
Exploring Fine-Tuning for In-Context Retrieval and Efficient KV-Caching in Long-Context Language Models
Francesco Maria Molfese, Momchil Hardalov, Rexhina Blloshmi +2
With context windows of millions of tokens, Long-Context Language Models (LCLMs) can encode entire document collections, offering a strong alternative to conventional retrieval-aug…
Correct, Concise and Complete: Multi-stage Training For Adaptive Reasoning
Nathanaël Carraz Rakotonirina, Ren Pang, Neha Anna John +2
The reasoning capabilities of large language models (LLMs) have improved substantially through increased test-time computation, typically in the form of intermediate tokens known a…
Understanding and Improving Information Preservation in Prompt Compression for LLMs
Weronika Åajewska, Momchil Hardalov, Laura Aina +3
Recent advancements in large language models (LLMs) have enabled their successful application to a broad range of tasks. However, in information-intensive tasks, the prompt length…