arXiv subjects

Gonzalo Iglesias

Publications and source records attributed to Gonzalo Iglesias.

7 recordsLinked to original sources

arXiv2026

Where Should a Document Live: Context, Representations, or Parameters?

To answer questions outside of their pre-training data, large language models (LLMs) need access to new information, which can be presented in the context window as documents, encoded into the model's parameters, or injected as latent representations. However, each of these methods comes with different efficiency, cost, and performance trade-offs, with no single winner. We present a controlled comparison of representation-based (KV-cache based) and parametric (fine-tuning-based) adaptation methods on five knowledge-intensive benchmarks. We show that in the oracle setting, Cartridges (KV) are the most accurate injection method at nearly every storage budget, outperforming parametric methods by 10 points. Compaction (KV) matches Cartridges only at low compression rates, lagging behind the parametric methods by 10 points at rates higher than $50\times$. In the more realistic multi-document retrieval scenario, Cartridges are the only method that matches in-context learning (ICL), leading the parametric methods by 29 points and Compaction by 15 points. Nonetheless, Cartridges are also the only method, besides full fine-tuning and large MLP adapters, that suffers from catastrophic forgetting, i.e., a 6% performance degradation on control benchmarks, with 13% in coding.

cs.CL↗

arXiv2026

Cartridges at Scale: Training Modular KV Caches over Large Document Collections

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 distilling document collections into reusable key-value (KV) caches that eliminate prefilling while preserving accuracy. A critical limitation of this approach is that cartridges are monolithic and non-compositional: encoding an entire collection into a single KV block does not scale, and naively mixing cartridges trained in isolation collapses performance to near chance. We introduce Cartridges at Scale (CAS), a training framework for scalable multi-cartridge learning with dynamic distractor mixing and a memory-efficient budget manager that rotates hundreds of per-document cartridges between GPU and persistent storage. Our approach scales to collections exceeding a million tokens, improving over a monolithic cartridge by 10-31 points at comparable token budgets. Oracle cartridge accuracy falls within 2-6 points of full in-context learning even at high compression. When paired with retrieval for cartridge selection, CAS matches or exceeds conventional RAG accuracy while consuming 3-4x fewer prompt tokens.

cs.CL↗

arXiv2026

Benchmarking Deflection and Hallucination in Large Vision-Language Models

Large Vision-Language Models (LVLMs) increasingly rely on retrieval to answer knowledge-intensive multimodal questions. Existing benchmarks overlook conflicts between visual and textual evidence and the importance of generating deflections (e.g., Sorry, I cannot answer...) when retrieved knowledge is incomplete. These benchmarks also suffer from rapid obsolescence, as growing LVLM training sets allow models to answer many questions without retrieval. We address these gaps with three contributions. First, we propose a dynamic data curation pipeline that preserves benchmark difficulty over time by filtering for genuinely retrieval-dependent samples. Second, we introduce VLM-DeflectionBench, a benchmark of 2,775 samples spanning diverse multimodal retrieval settings, designed to probe model behaviour under conflicting or insufficient evidence. Third, we define a fine-grained evaluation protocol with four scenarios that disentangle parametric memorization from retrieval robustness. Experiments across 20 state-of-the-art LVLMs indicate that models usually fail to deflect in the presence of noisy or misleading evidence. Our results highlight the need to evaluate not only what models know, but how they behave when they do not, and serve as a reusable and extensible benchmark for reliable KB-VQA evaluation. All resources will be publicly available upon publication.

cs.CL↗

arXiv2018

Neural Machine Translation Decoding with Terminology Constraints

Despite the impressive quality improvements yielded by neural machine translation (NMT) systems, controlling their translation output to adhere to user-provided terminology constraints remains an open problem. We describe our approach to constrained neural decoding based on finite-state machines and multi-stack decoding which supports target-side constraints as well as constraints with corresponding aligned input text spans. We demonstrate the performance of our framework on multiple translation tasks and motivate the need for constrained decoding with attentions as a means of reducing misplacement and duplication when translating user constraints.

cs.CL↗

arXiv2018

Accelerating NMT Batched Beam Decoding with LMBR Posteriors for Deployment

We describe a batched beam decoding algorithm for NMT with LMBR n-gram posteriors, showing that LMBR techniques still yield gains on top of the best recently reported results with Transformers. We also discuss acceleration strategies for deployment, and the effect of the beam size and batching on memory and speed.

cs.CL↗

arXiv2018

Why not be Versatile? Applications of the SGNMT Decoder for Machine Translation

SGNMT is a decoding platform for machine translation which allows paring various modern neural models of translation with different kinds of constraints and symbolic models. In this paper, we describe three use cases in which SGNMT is currently playing an active role: (1) teaching as SGNMT is being used for course work and student theses in the MPhil in Machine Learning, Speech and Language Technology at the University of Cambridge, (2) research as most of the research work of the Cambridge MT group is based on SGNMT, and (3) technology transfer as we show how SGNMT is helping to transfer research findings from the laboratory to the industry, eg. into a product of SDL plc.

cs.CL↗

arXiv2016

Speed-Constrained Tuning for Statistical Machine Translation Using Bayesian Optimization

We address the problem of automatically finding the parameters of a statistical machine translation system that maximize BLEU scores while ensuring that decoding speed exceeds a minimum value. We propose the use of Bayesian Optimization to efficiently tune the speed-related decoding parameters by easily incorporating speed as a noisy constraint function. The obtained parameter values are guaranteed to satisfy the speed constraint with an associated confidence margin. Across three language pairs and two speed constraint values, we report overall optimization time reduction compared to grid and random search. We also show that Bayesian Optimization can decouple speed and BLEU measurements, resulting in a further reduction of overall optimization time as speed is measured over a small subset of sentences.

cs.CL↗