Elizabeth Black

Gerrit Quaremba, Amy Rechkemmer, Elizabeth Black et al.

In automated fact-checking (AFC), check-worthiness detection identifies claims requiring verification based on domain-specific criteria. On Wikipedia, this task instantiates as Citation Needed Detection (CND), which flags claims lacking supporting citations. However, existing research has largely overlooked lower-resource languages, and recent AFC pipelines rely on large language models (LLMs), which are inaccessible to low-resource organizations. We introduce MCN, a multilingual CND corpus spanning 18 languages across three resource levels, on which we conduct an extensive study of small decoder-based language models (SLMs). Our experiments show that SLMs fine-tuned with an encoder-style objective substantially outperform prompted LLMs across languages. We further present one of the first studies on cross-lingual CND, demonstrating that SLMs fine-tuned solely on English claims surpass LLMs, even with little to no target-language adaptation. Our findings have important implications for lower-resource Wikipedia communities and suggest that compact, task-specific models are preferable to LLMs for CND. We release all data and code at https://github.com/gerritq/mcn

Gerrit Quaremba, Elizabeth Black, Denny Vrandečić et al.

Automatically detecting machine-generated text (MGT) is critical to maintaining the knowledge integrity of user-generated content (UGC) platforms such as Wikipedia. Existing detection benchmarks primarily focus on \textit{generic} text generation tasks (e.g., ``Write an article about machine learning.''). However, editors frequently employ LLMs for specific writing tasks (e.g., summarisation). These \textit{task-specific} MGT instances tend to resemble human-written text more closely due to their constrained task formulation and contextual conditioning. In this work, we show that a range of SOTA MGT detectors struggle to identify task-specific MGT reflecting real-world editing on Wikipedia. We introduce \textsc{TSM-Bench}, a multilingual, multi-generator, and \textit{multi-task} benchmark for evaluating MGT detectors on common, real-world Wikipedia editing tasks. Our findings demonstrate that (\textit{i}) average detection accuracy drops by 10--40\% compared to prior benchmarks, and (\textit{ii}) a generalisation asymmetry exists: fine-tuning on task-specific data enables generalisation to generic data -- even across domains -- but not vice versa. We demonstrate that models fine-tuned exclusively on generic MGT overfit to superficial artefacts of machine generation. Our results suggest that, in contrast to prior benchmarks, most detectors remain unreliable for automated detection in real-world contexts such as UGC platforms. \textsc{TSM-Bench} therefore provides a critical foundation for developing and evaluating future models.

Gabriele La Malfa, Emanuele La Malfa, Saar Cohen et al.

Self-play red team is an established approach to improving AI safety in which different instances of the same model play attacker and defender roles in a zero-sum game, i.e., where the attacker tries to jailbreak the defender; if self-play converges to a Nash equilibrium, the model is guaranteed to respond safely within the settings of the game. Although the parameter sharing enforced by the use of the same model for the two roles improves stability and performance, it introduces fundamental theoretical and architectural limitations. We show that the set of Nash equilibria that can be reached corresponds to a broad class of behaviours that includes trivial always refuse strategies and oracle-like defenders, thus limiting practical applicability. We then show that when attacker and defender share and update the same base model, the dynamics collapse to self-consistency, so that attacks do not enforce adversarial pressure on the defender. In response, we propose Anchored Bipolicy Self-Play, which trains distinct role-specific LoRA adapters on top of a frozen base model, thereby maintaining stable optimisation while preserving adversarial pressure through explicit role separation. In relation to standard self-play, we show up to 100x greater parameter efficiency than finetuning and consistent improvements in safety compared to self-play fine-tuned models. We evaluate on Qwen2.5-{3B, 7B,14B}-IT models across widely used safety benchmarks, showing improved robustness without loss of reasoning ability. Cross-play experiments further show that our attacker and defender models are superior to self-play in terms of adversarial defence and safety.

Emanuele La Malfa, Gabriele La Malfa, Samuele Marro et al. · oxford

Recent interest in Multi-Agent Systems of Large Language Models (MAS LLMs) has led to an increase in frameworks leveraging multiple LLMs to tackle complex tasks. However, much of this literature appropriates the terminology of MAS without engaging with its foundational principles. In this position paper, we highlight critical discrepancies between MAS theory and current MAS LLMs implementations, focusing on four key areas: the social aspect of agency, environment design, coordination and communication protocols, and measuring emergent behaviours. Our position is that many MAS LLMs lack multi-agent characteristics such as autonomy, social interaction, and structured environments, and often rely on oversimplified, LLM-centric architectures. The field may slow down and lose traction by revisiting problems the MAS literature has already addressed. Therefore, we systematically analyse this issue and outline associated research opportunities; we advocate for better integrating established MAS concepts and more precise terminology to avoid mischaracterisation and missed opportunities.

Gerrit Quaremba, Elizabeth Black, Denny Vrandečić et al.

Given Wikipedia's role as a trusted source of high-quality, reliable content, concerns are growing about the proliferation of low-quality machine-generated text (MGT) produced by large language models (LLMs) on its platform. Reliable detection of MGT is therefore essential. However, existing work primarily evaluates MGT detectors on generic generation tasks rather than on tasks more commonly performed by Wikipedia editors. This misalignment can lead to poor generalisability when applied in real-world Wikipedia contexts. We introduce WETBench, a multilingual, multi-generator, and task-specific benchmark for MGT detection. We define three editing tasks, empirically grounded in Wikipedia editors' perceived use cases for LLM-assisted editing: Paragraph Writing, Summarisation, and Text Style Transfer, which we implement using two new datasets across three languages. For each writing task, we evaluate three prompts, generate MGT across multiple generators using the best-performing prompt, and benchmark diverse detectors. We find that, across settings, training-based detectors achieve an average accuracy of 78%, while zero-shot detectors average 58%. These results show that detectors struggle with MGT in realistic generation scenarios and underscore the importance of evaluating such models on diverse, task-specific data to assess their reliability in editor-driven contexts.

Gabriele La Malfa, Jie M. Zhang, Michael Luck et al.

Fairness in multi-agent systems (MAS) focuses on equitable reward distribution among agents in scenarios involving sensitive attributes such as race, gender, or socioeconomic status. This paper introduces fairness in Proximal Policy Optimization (PPO) with a penalty term derived from a fairness definition such as demographic parity, counterfactual fairness, or conditional statistical parity. The proposed method, which we call Fair-PPO, balances reward maximisation with fairness by integrating two penalty components: a retrospective component that minimises disparities in past outcomes and a prospective component that ensures fairness in future decision-making. We evaluate our approach in two games: the Allelopathic Harvest, a cooperative and competitive MAS focused on resource collection, where some agents possess a sensitive attribute, and HospitalSim, a hospital simulation, in which agents coordinate the operations of hospital patients with different mobility and priority needs. Experiments show that Fair-PPO achieves fairer policies than PPO across the fairness metrics and, through the retrospective and prospective penalty components, reveals a wide spectrum of strategies to improve fairness; at the same time, its performance pairs with that of state-of-the-art fair reinforcement-learning algorithms. Fairness comes at the cost of reduced efficiency, but does not compromise equality among the overall population (Gini index). These findings underscore the potential of Fair-PPO to address fairness challenges in MAS.

Gabriele La Malfa, Jie M. Zhang, Michael Luck et al.

Fairness in Multi-Agent Systems (MAS) has been extensively studied, particularly in reward distribution among agents in scenarios such as goods allocation, resource division, lotteries, and bargaining systems. Fairness in MAS depends on various factors, including the system's governing rules, the behaviour of the agents, and their characteristics. Yet, fairness in human society often involves evaluating disparities between disadvantaged and privileged groups, guided by principles of Equality, Diversity, and Inclusion (EDI). Taking inspiration from the work on algorithmic fairness, which addresses bias in machine learning-based decision-making, we define protected attributes for MAS as characteristics that should not disadvantage an agent in terms of its expected rewards. We adapt fairness metrics from the algorithmic fairness literature -- namely, demographic parity, counterfactual fairness, and conditional statistical parity -- to the multi-agent setting, where self-interested agents interact within an environment. These metrics allow us to evaluate the fairness of MAS, with the ultimate aim of designing MAS that do not disadvantage agents based on protected attributes.