11 papers
AutoForest: Automatically Generating Forest Plots from Biomedical Studies with End-to-End Evidence Extraction and Synthesis
Massimiliano Pronesti, Angelo Miculescu, Mohsin Kapdi +8
Systematic reviews rely on forest plots to synthesise quantitative evidence across biomedical studies, but generating them remains a fragmented and labour-intensive process. Resear…
A Comparative Study of Controlled Text Generation Systems Using Level-Playing-Field Evaluation Principles
Michela Lorandi, Anya Belz
Background: Many different approaches to controlled text generation (CTG) have been proposed over recent years, but it is difficult to get a clear picture of which approach perform…
Output Composability of QLoRA PEFT Modules for Plug-and-Play Attribute-Controlled Text Generation
Michela Lorandi, Anya Belz
Parameter-efficient fine-tuning (PEFT) techniques offer task-specific fine-tuning at a fraction of the cost of full fine-tuning, but require separate fine-tuning for every new task…
Budgeted LoRA: Distillation as Structured Compute Allocation for Efficient Inference
Mohammed Sabry, Anya Belz
We study distillation for large language models under explicit compute constraints, with the goal of producing student models that are not only cheaper to train, but structurally e…
Induction Signatures Are Not Enough: A Matched-Compute Study of Load-Bearing Structure in In-Context Learning
Mohammed Sabry, Anya Belz
Mechanism-targeted synthetic data is increasingly proposed as a way to steer pretraining toward desirable capabilities, but it remains unclear how such interventions should be eval…
Beyond Outcome Verification: Verifiable Process Reward Models for Structured Reasoning
Massimiliano Pronesti, Anya Belz, Yufang Hou
Recent work on reinforcement learning with verifiable rewards (RLVR) has shown that large language models (LLMs) can be substantially improved using outcome-level verification sign…