activity
20242026
collaborators

11 papers

cs.CL2026

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…

cs.CL2026

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…

cs.CL2026

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…

cs.LG2026

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…

cs.CL2026

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…

cs.CL2026

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…