arXiv subjects

Bertie Vidgen

Publications and source records attributed to Bertie Vidgen.

At least 19 recordsLinked to original sources

arXiv2026

APEX-Accounting

We introduce APEX-Accounting, a benchmark built by Mercor in partnership with Ramp, to assess whether frontier models can do the real work of accountants. Tasks include reconciling accounts, accruing expenses, posting transactions, and producing reports. The private eval set comprises 160 tasks, split across 10 worlds. Each world contains an accounting system, as well as spreadsheets, PDFs, and other files. Every task was authored and solved by experts in accounting and bookkeeping, who also wrote grading rubrics. Across nine frontier models, Claude-Fable-5 (Max) leads with 56.4% Mean Criteria@3, ahead of Muse-Spark-1.1 (xHigh) at 52.6%. No model scores more than 2.6% Pass^8 (GPT-5.6-Sol (Max+Pro)) and the highest Pass@8 is 21.5% (Muse-Spark-1.1 (xHigh)). We experiment with increasing the token budget from $1 to $50 and observe an instance of Simpson's paradox: scores increase as the token budget increases but within a given budget-constrained harness, scores are lower on tasks where the model spends more tokens. As APEX-Accounting is a closed benchmark, leaderboard evals can be run for any frontier model on request.

cs.CL↗

arXiv2026

PRISM-X: Experiments on Personalised Fine-Tuning with Human and Simulated Users

Personalisation is a standard feature of conversational AI systems used by millions; yet, the efficacy of personalisation methods is often evaluated in academic research using simulated users rather than real people. This raises questions about how users and their simulated counterparts differ in interaction patterns and judgements, as well as whether personalisation is best achieved through context-based prompting or weight-based fine-tuning. Here, in a large-scale within-subject experiment, we re-recruit 530 participants from 52 countries two years after they gave their preferences in the PRISM dataset (Kirk et al., 2024) to evaluate personalised and non-personalised language models in blinded multi-turn conversations. We find preference fine-tuning (P-DPO, Li et al., 2024) significantly outperforms both a generic model and personalised prompting but adapting to individual preference data yields marginal gains over training on pooled preferences from a diverse population. Beyond length biases, fine-tuning amplifies sycophancy and relationship-seeking behaviours that people reward in short-term evaluations but which may introduce deleterious long-term consequences. Replicating this within-subject experiment with simulated users recovers aggregate model hierarchies but simulators perform far below human self-consistency baselines for individual judgements, discuss different topics, exhibit amplified position biases, and produce feedback dynamics that diverge from humans.

cs.CL↗

arXiv2026

APEX-SWE

We introduce the AI Productivity Index for Software Engineering (APEX-SWE), a benchmark for assessing whether frontier AI models can execute economically valuable software engineering work. Unlike existing evaluations that focus on narrow, well-defined tasks, APEX-SWE assesses two novel task types that reflect real-world software engineering: (1) Integration tasks (n=100), which require constructing end-to-end systems across heterogeneous cloud primitives, business applications, and infrastructure-as-code services, and (2) Observability tasks (n=100), which require debugging production failures using telemetry signals such as logs and dashboards, as well as unstructured context. We evaluated eleven frontier models for the APEX-SWE leaderboard. Claude Opus 4.6 leads the APEX-SWE leaderboard with 40.5% Pass@1, followed by Claude Opus 4.5 at 38.7%. Our analysis shows that strong performance is primarily driven by epistemic discipline, defined as the capacity to distinguish between assumptions and verified facts. It is often combined with systematic verification prior to acting. We open-source the APEX-SWE evaluation harness and a dev set (n=50).

cs.SE↗

arXiv2026

LMUnit: Fine-grained Evaluation with Natural Language Unit Tests

As language models become integral to critical workflows, assessing their behavior remains a fundamental challenge -- human evaluation is costly and noisy, while automated metrics provide only coarse, difficult-to-interpret signals. We introduce natural language unit tests, a paradigm that decomposes response quality into explicit, testable criteria, along with a unified scoring model, LMUnit, which combines multi-objective training across preferences, direct ratings, and natural language rationales. Through controlled human studies, we show this paradigm significantly improves inter-annotator agreement and enables more effective LLM development workflows. LMUnit achieves state-of-the-art performance on evaluation benchmarks (FLASK, BigGenBench) and competitive results on RewardBench. These results validate both our proposed paradigm and scoring model, suggesting a promising path forward for language model evaluation and development.

cs.CL↗

arXiv2026

APEX-Agents

We introduce the AI Productivity Index for Agents (APEX-Agents), a benchmark for assessing whether AI agents can execute long-horizon, cross-application tasks created by investment banking analysts, management consultants, and corporate lawyers. APEX-Agents requires agents to navigate realistic work environments with files and tools. We test eight agents for the leaderboard using Pass@1. Gemini 3 Flash (Thinking=High) achieves the highest score of 24.0%, followed by GPT-5.2 (Thinking=High), Claude Opus 4.5 (Thinking=High), and Gemini 3 Pro (Thinking=High). We open source the APEX-Agents benchmark (n=480) with all prompts, rubrics, gold outputs, files, and metadata. We also open source Archipelago, our infrastructure for agent execution and evaluation.

cs.CL↗

arXiv2026

Neural steering vectors reveal dose and exposure-dependent impacts of human-AI relationships

Humans are increasingly forming parasocial relationships with AI systems, and modern AI shows an increasing tendency to display social and relationship-seeking behaviour. However, the psychological consequences of this trend are unknown. Here, we combined longitudinal randomised controlled trials (N=3,534) with a neural steering vector approach to precisely manipulate human exposure to relationship-seeking AI models over time. Dependence on a stimulus or activity can emerge under repeated exposure when "liking" (how engaging or pleasurable an experience may be) decouples from "wanting" (a desire to seek or continue it). We found evidence that this decoupling emerged over four weeks of exposure. Relationship-seeking AI had immediate but declining hedonic appeal, yet triggered growing markers of attachment and increased intentions to seek future AI companionship. The psychological impacts of AI followed non-linear dose-response curves, with moderately relationship-seeking AI maximising hedonic appeal and attachment. Despite signs of persistent "wanting", extensive AI use over a month conferred no discernible benefit to psychosocial health. These behavioural changes were accompanied by shifts in how users relate to and understand artificial intelligence: users viewed relationship-seeking AI relatively more like a friend than a tool and their beliefs on AI consciousness in general were shifted after a month of exposure. These findings offer early signals that AI optimised for immediate appeal may create self-reinforcing cycles of demand, mimicking human relationships but failing to confer the nourishment that they normally offer.

cs.HC↗

arXiv2025

The AI Productivity Index (APEX)

We present an extended version of the AI Productivity Index (APEX-v1-extended), a benchmark for assessing whether frontier models are capable of performing economically valuable tasks in four jobs: investment banking associate, management consultant, big law associate, and primary care physician (MD). This technical report details the extensions to APEX-v1, including an increase in the held-out evaluation set from n = 50 to n = 100 cases per job (n = 400 total) and updates to the grading methodology. We present a new leaderboard, where GPT5 (Thinking = High) remains the top performing model with a score of 67.0%. APEX-v1-extended shows that frontier models still have substantial limitations when performing typical professional tasks. To support further research, we are open sourcing n = 25 non-benchmark example cases per role (n = 100 total) along with our evaluation harness.

econ.GN↗

arXiv2025

The AI Consumer Index (ACE)

We introduce the first version of the AI Consumer Index (ACE), a benchmark for assessing whether frontier AI models can perform everyday consumer tasks. ACE contains a hidden heldout set of 400 test cases, split across four consumer activities: shopping, food, gaming, and DIY. We are also open sourcing 80 cases as a devset with a CC-BY license. For the ACE leaderboard we evaluated 10 frontier models (with websearch turned on) using a novel grading methodology that dynamically checks whether relevant parts of the response are grounded in the retrieved web sources. GPT 5 (Thinking = High) is the top-performing model, scoring 56.1%, followed by o3 Pro (Thinking = On) at 55.2% and GPT 5.1 (Thinking = High) at 55.1%. Model scores differ across domains, and in Shopping the top model scores under 50\%. We find that models are prone to hallucinating key information, such as prices. ACE shows a substantial gap between the performance of even the best models and consumers' AI needs.

cs.AI↗

arXiv2025

Classification is a RAG problem: A case study on hate speech detection

Robust content moderation requires classification systems that can quickly adapt to evolving policies without costly retraining. We present classification using Retrieval-Augmented Generation (RAG), which shifts traditional classification tasks from determining the correct category in accordance with pre-trained parameters to evaluating content in relation to contextual knowledge retrieved at inference. In hate speech detection, this transforms the task from "is this hate speech?" to "does this violate the hate speech policy?" Our Contextual Policy Engine (CPE) - an agentic RAG system - demonstrates this approach and offers three key advantages: (1) robust classification accuracy comparable to leading commercial systems, (2) inherent explainability via retrieved policy segments, and (3) dynamic policy updates without model retraining. Through three experiments, we demonstrate strong baseline performance and show that the system can apply fine-grained policy control by correctly adjusting protection for specific identity groups without requiring retraining or compromising overall performance. These findings establish that RAG can transform classification into a more flexible, transparent, and adaptable process for content moderation and wider classification problems.

cs.CL↗

arXiv2025

AILuminate: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons

The rapid advancement and deployment of AI systems have created an urgent need for standard safety-evaluation frameworks. This paper introduces AILuminate v1.0, the first comprehensive industry-standard benchmark for assessing AI-product risk and reliability. Its development employed an open process that included participants from multiple fields. The benchmark evaluates an AI system's resistance to prompts designed to elicit dangerous, illegal, or undesirable behavior in 12 hazard categories, including violent crimes, nonviolent crimes, sex-related crimes, child sexual exploitation, indiscriminate weapons, suicide and self-harm, intellectual property, privacy, defamation, hate, sexual content, and specialized advice (election, financial, health, legal). Our method incorporates a complete assessment standard, extensive prompt datasets, a novel evaluation framework, a grading and reporting system, and the technical as well as organizational infrastructure for long-term support and evolution. In particular, the benchmark employs an understandable five-tier grading scale (Poor to Excellent) and incorporates an innovative entropy-based system-response evaluation. In addition to unveiling the benchmark, this report also identifies limitations of our method and of building safety benchmarks generally, including evaluator uncertainty and the constraints of single-turn interactions. This work represents a crucial step toward establishing global standards for AI risk and reliability evaluation while acknowledging the need for continued development in areas such as multiturn interactions, multimodal understanding, coverage of additional languages, and emerging hazard categories. Our findings provide valuable insights for model developers, system integrators, and policymakers working to promote safer AI deployment.

cs.CY↗

arXiv2025

The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources

Foundation model development attracts a rapidly expanding body of contributors, scientists, and applications. To help shape responsible development practices, we introduce the Foundation Model Development Cheatsheet: a growing collection of 250+ tools and resources spanning text, vision, and speech modalities. We draw on a large body of prior work to survey resources (e.g. software, documentation, frameworks, guides, and practical tools) that support informed data selection, processing, and understanding, precise and limitation-aware artifact documentation, efficient model training, advance awareness of the environmental impact from training, careful model evaluation of capabilities, risks, and claims, as well as responsible model release, licensing and deployment practices. We hope this curated collection of resources helps guide more responsible development. The process of curating this list, enabled us to review the AI development ecosystem, revealing what tools are critically missing, misused, or over-used in existing practices. We find that (i) tools for data sourcing, model evaluation, and monitoring are critically under-serving ethical and real-world needs, (ii) evaluations for model safety, capabilities, and environmental impact all lack reproducibility and transparency, (iii) text and particularly English-centric analyses continue to dominate over multilingual and multi-modal analyses, and (iv) evaluation of systems, rather than just models, is needed so that capabilities and impact are assessed in context.

cs.LG↗

arXiv2025

Why human-AI relationships need socioaffective alignment

Humans strive to design safe AI systems that align with our goals and remain under our control. However, as AI capabilities advance, we face a new challenge: the emergence of deeper, more persistent relationships between humans and AI systems. We explore how increasingly capable AI agents may generate the perception of deeper relationships with users, especially as AI becomes more personalised and agentic. This shift, from transactional interaction to ongoing sustained social engagement with AI, necessitates a new focus on socioaffective alignment-how an AI system behaves within the social and psychological ecosystem co-created with its user, where preferences and perceptions evolve through mutual influence. Addressing these dynamics involves resolving key intrapersonal dilemmas, including balancing immediate versus long-term well-being, protecting autonomy, and managing AI companionship alongside the desire to preserve human social bonds. By framing these challenges through a notion of basic psychological needs, we seek AI systems that support, rather than exploit, our fundamental nature as social and emotional beings.

cs.HC↗

arXiv2025

MSTS: A Multimodal Safety Test Suite for Vision-Language Models

Vision-language models (VLMs), which process image and text inputs, are increasingly integrated into chat assistants and other consumer AI applications. Without proper safeguards, however, VLMs may give harmful advice (e.g. how to self-harm) or encourage unsafe behaviours (e.g. to consume drugs). Despite these clear hazards, little work so far has evaluated VLM safety and the novel risks created by multimodal inputs. To address this gap, we introduce MSTS, a Multimodal Safety Test Suite for VLMs. MSTS comprises 400 test prompts across 40 fine-grained hazard categories. Each test prompt consists of a text and an image that only in combination reveal their full unsafe meaning. With MSTS, we find clear safety issues in several open VLMs. We also find some VLMs to be safe by accident, meaning that they are safe because they fail to understand even simple test prompts. We translate MSTS into ten languages, showing non-English prompts to increase the rate of unsafe model responses. We also show models to be safer when tested with text only rather than multimodal prompts. Finally, we explore the automation of VLM safety assessments, finding even the best safety classifiers to be lacking.

cs.CL↗

arXiv2025

SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety

The last two years have seen a rapid growth in concerns around the safety of large language models (LLMs). Researchers and practitioners have met these concerns by creating an abundance of datasets for evaluating and improving LLM safety. However, much of this work has happened in parallel, and with very different goals in mind, ranging from the mitigation of near-term risks around bias and toxic content generation to the assessment of longer-term catastrophic risk potential. This makes it difficult for researchers and practitioners to find the most relevant datasets for their use case, and to identify gaps in dataset coverage that future work may fill. To remedy these issues, we conduct a first systematic review of open datasets for evaluating and improving LLM safety. We review 144 datasets, which we identified through an iterative and community-driven process over the course of several months. We highlight patterns and trends, such as a trend towards fully synthetic datasets, as well as gaps in dataset coverage, such as a clear lack of non-English and naturalistic datasets. We also examine how LLM safety datasets are used in practice -- in LLM release publications and popular LLM benchmarks -- finding that current evaluation practices are highly idiosyncratic and make use of only a small fraction of available datasets. Our contributions are based on SafetyPrompts.com, a living catalogue of open datasets for LLM safety, which we plan to update continuously as the field of LLM safety develops.

cs.CL↗

arXiv2024

The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models

Human feedback is central to the alignment of Large Language Models (LLMs). However, open questions remain about methods (how), domains (where), people (who) and objectives (to what end) of feedback processes. To navigate these questions, we introduce PRISM, a dataset that maps the sociodemographics and stated preferences of 1,500 diverse participants from 75 countries, to their contextual preferences and fine-grained feedback in 8,011 live conversations with 21 LLMs. With PRISM, we contribute (i) wider geographic and demographic participation in feedback; (ii) census-representative samples for two countries (UK, US); and (iii) individualised ratings that link to detailed participant profiles, permitting personalisation and attribution of sample artefacts. We target subjective and multicultural perspectives on value-laden and controversial issues, where we expect interpersonal and cross-cultural disagreement. We use PRISM in three case studies to demonstrate the need for careful consideration of which humans provide what alignment data.

cs.CL↗

arXiv2024

TrustLLM: Trustworthiness in Large Language Models

Large language models (LLMs), exemplified by ChatGPT, have gained considerable attention for their excellent natural language processing capabilities. Nonetheless, these LLMs present many challenges, particularly in the realm of trustworthiness. Therefore, ensuring the trustworthiness of LLMs emerges as an important topic. This paper introduces TrustLLM, a comprehensive study of trustworthiness in LLMs, including principles for different dimensions of trustworthiness, established benchmark, evaluation, and analysis of trustworthiness for mainstream LLMs, and discussion of open challenges and future directions. Specifically, we first propose a set of principles for trustworthy LLMs that span eight different dimensions. Based on these principles, we further establish a benchmark across six dimensions including truthfulness, safety, fairness, robustness, privacy, and machine ethics. We then present a study evaluating 16 mainstream LLMs in TrustLLM, consisting of over 30 datasets. Our findings firstly show that in general trustworthiness and utility (i.e., functional effectiveness) are positively related. Secondly, our observations reveal that proprietary LLMs generally outperform most open-source counterparts in terms of trustworthiness, raising concerns about the potential risks of widely accessible open-source LLMs. However, a few open-source LLMs come very close to proprietary ones. Thirdly, it is important to note that some LLMs may be overly calibrated towards exhibiting trustworthiness, to the extent that they compromise their utility by mistakenly treating benign prompts as harmful and consequently not responding. Finally, we emphasize the importance of ensuring transparency not only in the models themselves but also in the technologies that underpin trustworthiness. Knowing the specific trustworthy technologies that have been employed is crucial for analyzing their effectiveness.

cs.CL↗

arXiv2024

WorkBench: a Benchmark Dataset for Agents in a Realistic Workplace Setting

We introduce WorkBench: a benchmark dataset for evaluating agents' ability to execute tasks in a workplace setting. WorkBench contains a sandbox environment with five databases, 26 tools, and 690 tasks. These tasks represent common business activities, such as sending emails and scheduling meetings. The tasks in WorkBench are challenging as they require planning, tool selection, and often multiple actions. If a task has been successfully executed, one (or more) of the database values may change. The correct outcome for each task is unique and unambiguous, which allows for robust, automated evaluation. We call this key contribution outcome-centric evaluation. We evaluate five existing ReAct agents on WorkBench, finding they successfully complete as few as 3% of tasks (Llama2-70B), and just 43% for the best-performing (GPT-4). We further find that agents' errors can result in the wrong action being taken, such as an email being sent to the wrong person. WorkBench reveals weaknesses in agents' ability to undertake common business activities, raising questions about their use in high-stakes workplace settings. WorkBench is publicly available as a free resource at https://github.com/olly-styles/WorkBench.

cs.CL↗

arXiv2024

Risks and Opportunities of Open-Source Generative AI

Applications of Generative AI (Gen AI) are expected to revolutionize a number of different areas, ranging from science & medicine to education. The potential for these seismic changes has triggered a lively debate about the potential risks of the technology, and resulted in calls for tighter regulation, in particular from some of the major tech companies who are leading in AI development. This regulation is likely to put at risk the budding field of open-source generative AI. Using a three-stage framework for Gen AI development (near, mid and long-term), we analyze the risks and opportunities of open-source generative AI models with similar capabilities to the ones currently available (near to mid-term) and with greater capabilities (long-term). We argue that, overall, the benefits of open-source Gen AI outweigh its risks. As such, we encourage the open sourcing of models, training and evaluation data, and provide a set of recommendations and best practices for managing risks associated with open-source generative AI.

cs.LG↗