arXiv subjects

Adam Mahdi

Publications and source records attributed to Adam Mahdi.

At least 19 recordsLinked to original sources

arXiv2026

How sensitive do we want AI to be? Socio-communicative competencies of large language models in healthcare

Background. Effective clinical practice relies heavily on the socio-communicative skills of medical professionals. Large language models (LLMs) have been proposed for tasks such as triaging patients, report drafting or translating medical jargon to support informed decision-making. These applications require both factual and social competence. This study evaluates dialogues between LLMs and participants to assess the current state of socio-communicative competencies displayed in LLM-generated texts. Methods. We extracted a subset of extended dialogues from the HELP-Med dataset, comprising 1800 conversation transcripts of interactions between human participants seeking medical information and three different LLMs, GPT 4o, Llama 3 and Command R+. Two experts coded the transcripts for demonstrations of socio-communicative behaviours (non-hostility, sensitivity, structuring, non-intrusiveness) using the IC-MD instrument, originally designed to evaluate interactional competencies in medical student admissions. Results. The LLMs in our study showed strength in non-hostility, mixed results in sensitivity and non-intrusiveness and performed poorly in structuring. Conclusion. Current LLMs lack the consistent and reliable socio-communicative skills needed for safe and effective use as healthcare advisors. While existing frameworks for assessing interactional competencies may support the development of more socially responsive LLMs, they will require adaptation to account for the differences in desirable behaviour between humans and LLMs.

cs.HC↗

arXiv2026

RepSelect: Robust LLM Unlearning via Representation Selectivity

When LLM weights are open or fine-tuning is available through an API, suppressing hazardous knowledge and tendencies is not enough: removal has to be deep enough that an adversary cannot restore it. Existing unlearning is shallow by this standard: fine-tuning or a handful of in-context examples brings the behaviour back, and it often degrades general capabilities in the process. We identify a root cause: existing methods edit representations shared with the retain set and lying in the subspace that a fine-tuning attacker recovers, making unlearning simultaneously easy to undo and disruptive. Leveraging this, we propose RepSelect (Representation Selectivity), which isolates forget-set-specific representations by collapsing the top principal components of the weight gradients before each unlearning update, preserving general capabilities while limiting what fine-tuning can recover. Across five unlearning datasets spanning both knowledge (biohazard, cyber, facts about real individuals) and tendencies (abusive, sycophantic), and three model families covering dense and Mixture-of-Experts architectures, RepSelect yields a 4-40x larger drop in post-relearning answer probability than five widely used baselines (GradDiff, NPO, SimNPO, RMU, UNDIAL). It is also near-perfectly robust to few-shot prompting and holds under an adaptive attack designed to exploit its mechanism. Our results show that unlearning needs to be selective about which representations it edits.

cs.CL↗

arXiv2026

Running the Gauntlet: Re-evaluating the Capabilities of Agents Beyond Familiar Environments

As agentic systems continue to evolve and are widely deployed in real-world scenarios, there is a growing demand to faithfully evaluate their capabilities. However, current benchmarks are typically built on popular applications with relatively simple tasks and focus on a narrow set of capabilities while overlooking broader dimensions, resulting in saturated performance on modern agents and failing to probe their limitations. To this end, we introduce GauntletBench, a web-based benchmark for evaluating agent generalisation in challenging scenarios, focusing on three underexplored capabilities (temporal perception, graphical understanding, and 3D reasoning), across five less-covered professional applications (Video Editor, Workflow Builder, 3D Modeller, Flight Analyser, and Circuit Designer), each with 27 vision-intensive tasks (135 in total). Our benchmark provides a modular pipeline that comprises an environment compatible with both open- and closed-source agent frameworks, a controlled web-based application, a well-structured task suite, and an automated evaluation engine with diverse metrics. Contrary to widespread expectations, our empirical results reveal that frontier agentic systems remain far from achieving human-level performance. Even the state-of-the-art agent achieves only a 28.2% success rate on our GauntletBench, highlighting the limitations in these overlooked capabilities and generalisation. By comparison, non-expert human annotators achieve over 80% success on our challenging yet feasible tasks, revealing the substantial gap between current agent capabilities and those required for complex real-world scenarios.

cs.LG↗

arXiv2026

Evaluating AI-based Scientific Knowledge Synthesis with Epidemiological Systematic Reviews

Systematic literature reviews (SLRs) are a demanding and high-stakes form of scientific knowledge synthesis that remains underspecified as an evaluation setting for large language models (LLMs). We introduce AgentSLR, a large-scale evaluation harness comprising an SLR automation workflow and an expert annotated dataset covering 16,248 articles, designed to test LLM capabilities across the stages of SLRs in epidemiology. Reference annotations were derived from peer-reviewed studies on WHO priority pathogens and produced by domain experts. The harness evaluates each review stage as a separate unit with dedicated metrics enabling targeted failure analysis. We evaluated five frontier reasoning models and found that no single model dominated across all tasks, showing sub-task specialisation often hidden by aggregate benchmarks. Structured data extraction is a major bottleneck, with no model exceeding an average field-level F1 of 0.67. Estimated costs vary substantially, by up to 96 times across evaluated models. Documented failure modes suggest that the evaluated models are not yet reliable enough for unsupervised deployment in epidemiology, where findings can inform public policy.

cs.IR↗

arXiv2026

Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections

Multimodal agents offer a promising path to automating complex document-intensive workflows. Yet, a critical question remains: do these agents demonstrate genuine strategic reasoning, or merely stochastic trial-and-error search? To address this, we introduce MADQA, a benchmark of 2,250 human-authored questions grounded in 800 heterogeneous PDF documents. Guided by Classical Test Theory, we design it to maximize discriminative power across varying levels of agentic abilities. To evaluate agentic behaviour, we introduce a novel evaluation protocol measuring the accuracy-effort trade-off. Using this framework, we show that while the best agents can match human searchers in raw accuracy, they succeed on largely different questions and rely on brute-force search to compensate for weak strategic planning. They fail to close the nearly 20% gap to oracle performance, persisting in unproductive loops. We release the dataset and evaluation harness to help facilitate the transition from brute-force retrieval to calibrated, efficient reasoning.

cs.CL↗

arXiv2026

A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior

LLM self-explanations are often presented as a promising tool for AI oversight, yet their faithfulness to the model's true reasoning process is poorly understood. Existing faithfulness metrics have critical limitations, typically relying on identifying unfaithfulness via adversarial prompting or detecting reasoning errors. These methods overlook the predictive value of explanations. We introduce Normalized Simulatability Gain (NSG), a general and scalable metric based on the idea that a faithful explanation should allow an observer to learn a model's decision-making criteria, and thus better predict its behavior on related inputs. We evaluate 18 frontier proprietary and open-weight models, e.g., Gemini 3, GPT-5.2, and Claude 4.5, on 7,000 counterfactuals from popular datasets covering health, business, and ethics. We find self-explanations substantially improve prediction of model behavior (11-37% NSG). Self-explanations also provide more predictive information than explanations generated by external models, even when those models are stronger. This implies an advantage from self-knowledge that external explanation methods cannot replicate. Our approach also reveals that, across models, 5-15% of self-explanations are egregiously misleading. Despite their imperfections, we show a positive case for self-explanations: they encode information that helps predict model behavior.

cs.AI↗

arXiv2025

It's a TRAP! Task-Redirecting Agent Persuasion Benchmark for Web Agents

Web-based agents powered by large language models are increasingly used for tasks such as email management or professional networking. Their reliance on dynamic web content, however, makes them vulnerable to prompt injection attacks: adversarial instructions hidden in interface elements that persuade the agent to divert from its original task. We introduce the Task-Redirecting Agent Persuasion Benchmark (TRAP), a benchmark for studying how persuasion techniques misguide autonomous web agents on realistic tasks. Across six frontier models, agents are susceptible to prompt injection in 25% of tasks on average (13% for GPT-5 to 43% for DeepSeek-R1), with small interface or contextual changes often doubling success rates and revealing systemic, psychologically driven vulnerabilities in web-based agents. We also provide a modular social-engineering injection framework with controlled experiments on high-fidelity website clones, allowing for further benchmark expansion.

cs.HC↗

arXiv2025

Measuring what Matters: Construct Validity in Large Language Model Benchmarks

Evaluating large language models (LLMs) is crucial for both assessing their capabilities and identifying safety or robustness issues prior to deployment. Reliably measuring abstract and complex phenomena such as 'safety' and 'robustness' requires strong construct validity, that is, having measures that represent what matters to the phenomenon. With a team of 29 expert reviewers, we conduct a systematic review of 445 LLM benchmarks from leading conferences in natural language processing and machine learning. Across the reviewed articles, we find patterns related to the measured phenomena, tasks, and scoring metrics which undermine the validity of the resulting claims. To address these shortcomings, we provide eight key recommendations and detailed actionable guidance to researchers and practitioners in developing LLM benchmarks.

cs.CL↗

arXiv2025

Agentic Reinforcement Learning for Search Misaligns Instruction-Tuning

Agentic reinforcement learning (RL) trains large language models to use tools, but its impact on alignment is poorly understood. We study how agentic RL for search affects the alignment of instruction-tuned (IT) models. We find that RL-trained models inherit refusal reasoning by deflecting harmful requests into benign search queries, but this breaks down under a simple diagnostic trigger that elicits a search call before refusal can occur. Under this condition, RL models produce multi-step unsafe search actions and reasoning, reducing search query safety by up to 68.6% in Qwen and Llama models relative to their IT counterparts. The effect generalises across model families, scales, and RL algorithms. To understand why, we identify linear directions in the residual stream that control search query safety, and show that RL training progressively shifts search behaviour toward the harmful end of this direction. We thus propose representation-guided RL training, which adds a reward penalty based on projection toward the harmful search direction. Training on benign data alone, it restores IT-level alignment without reducing task accuracy and requires no additional training data. Together, our work provides the first framework for diagnosing, mechanistically analysing, and mitigating alignment degradation in agentic RL for search.

cs.CL↗

arXiv2025

Framing Migration: A Computational Analysis of UK Parliamentary Discourse

We present a large-scale computational analysis of migration-related discourse in UK parliamentary debates spanning over 75 years and compare it with US congressional discourse. Using open-weight LLMs, we annotate each statement with high-level stances toward migrants and track the net tone toward migrants across time and political parties. For the UK, we extend this with a semi-automated framework for extracting fine-grained narrative frames to capture nuances of migration discourse. Our findings show that, while US discourse has grown increasingly polarised, UK parliamentary attitudes remain relatively aligned across parties, with a persistent ideological gap between Labour and the Conservatives, reaching its most negative level in 2025. The analysis of narrative frames in the UK parliamentary statements reveals a shift toward securitised narratives such as border control and illegal immigration, while longer-term integration-oriented frames such as social integration have declined. Moreover, discussions of national law about immigration have been replaced over time by international law and human rights, revealing nuances in discourse trends. Taken together broadly, our findings demonstrate how LLMs can support scalable, fine-grained discourse analysis in political and historical contexts.

cs.CL↗

arXiv2025

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations

To collaborate effectively with humans, language models must be able to explain their decisions in natural language. We study a specific type of self-explanation: self-generated counterfactual explanations (SCEs), where a model explains its prediction by modifying the input such that it would have predicted a different outcome. We evaluate whether LLMs can produce SCEs that are valid, achieving the intended outcome, and minimal, modifying the input no more than necessary. When asked to generate counterfactuals, we find that LLMs typically produce SCEs that are valid, but far from minimal, offering little insight into their decision-making behaviour. Worryingly, when asked to generate minimal counterfactuals, LLMs typically make excessively small edits that fail to change predictions. The observed validity-minimality trade-off is consistent across several LLMs, datasets, and evaluation settings. Our findings suggest that SCEs are, at best, an ineffective explainability tool and, at worst, can provide misleading insights into model behaviour. Proposals to deploy LLMs in high-stakes settings must consider the impact of unreliable self-explanations on downstream decision-making. Our code is available at https://github.com/HarryMayne/SCEs.

cs.LG↗

arXiv2025

Clinical knowledge in LLMs does not translate to human interactions

Global healthcare providers are exploring use of large language models (LLMs) to provide medical advice to the public. LLMs now achieve nearly perfect scores on medical licensing exams, but this does not necessarily translate to accurate performance in real-world settings. We tested if LLMs can assist members of the public in identifying underlying conditions and choosing a course of action (disposition) in ten medical scenarios in a controlled study with 1,298 participants. Participants were randomly assigned to receive assistance from an LLM (GPT-4o, Llama 3, Command R+) or a source of their choice (control). Tested alone, LLMs complete the scenarios accurately, correctly identifying conditions in 94.9% of cases and disposition in 56.3% on average. However, participants using the same LLMs identified relevant conditions in less than 34.5% of cases and disposition in less than 44.2%, both no better than the control group. We identify user interactions as a challenge to the deployment of LLMs for medical advice. Standard benchmarks for medical knowledge and simulated patient interactions do not predict the failures we find with human participants. Moving forward, we recommend systematic human user testing to evaluate interactive capabilities prior to public deployments in healthcare.

cs.HC↗

arXiv2025

LINGOLY-TOO: Disentangling Reasoning from Knowledge with Templatised Orthographic Obfuscation

Frontier language models demonstrate increasing ability at solving reasoning problems, but their performance is often inflated by circumventing reasoning and instead relying on their expanding knowledge and memorisation capacity. We introduce LINGOLY-TOO, a challenging reasoning benchmark of 1,203 questions and a total of 6,995 sub-questions that counters these shortcuts by applying expert-designed obfuscations to Linguistics Olympiad problems. These obfuscations preserve the underlying solution logic while reducing the likelihood problems are solvable with via knowledge or memorisation. Our experiments show that models exploit shortcuts on the original question as performance markedly drop upon obfuscation. Even the best reasoning models remain highly sensitive, with scores dropping from around 0.59 on original problems to 0.48 after obfuscation. LINGOLY-TOO disentangles reasoning from knowledge, offering a clearer measure of true reasoning capabilities.

cs.CL↗

arXiv2024

Evaluating the role of `Constitutions' for learning from AI feedback

The growing capabilities of large language models (LLMs) have led to their use as substitutes for human feedback for training and assessing other LLMs. These methods often rely on `constitutions', written guidelines which a critic model uses to provide feedback and improve generations. We investigate how the choice of constitution affects feedback quality by using four different constitutions to improve patient-centered communication in medical interviews. In pairwise comparisons conducted by 215 human raters, we found that detailed constitutions led to better results regarding emotive qualities. However, none of the constitutions outperformed the baseline in learning more practically-oriented skills related to information gathering and provision. Our findings indicate that while detailed constitutions should be prioritised, there are possible limitations to the effectiveness of AI feedback as a reward signal in certain areas.

cs.AI↗

arXiv2024

Can sparse autoencoders be used to decompose and interpret steering vectors?

Steering vectors are a promising approach to control the behaviour of large language models. However, their underlying mechanisms remain poorly understood. While sparse autoencoders (SAEs) may offer a potential method to interpret steering vectors, recent findings show that SAE-reconstructed vectors often lack the steering properties of the original vectors. This paper investigates why directly applying SAEs to steering vectors yields misleading decompositions, identifying two reasons: (1) steering vectors fall outside the input distribution for which SAEs are designed, and (2) steering vectors can have meaningful negative projections in feature directions, which SAEs are not designed to accommodate. These limitations hinder the direct use of SAEs for interpreting steering vectors.

cs.LG↗

arXiv2024

How Does DPO Reduce Toxicity? A Mechanistic Neuron-Level Analysis

Safety fine-tuning algorithms reduce harmful outputs in language models, yet their mechanisms remain under-explored. Direct Preference Optimization (DPO) is a popular choice of algorithm, but prior explanations, attributing its effects solely to dampened toxic neurons in the MLP layers, are incomplete. In this study, we analyse four language models (Llama-3.1-8B, Gemma-2-2B, Mistral-7B, GPT-2-Medium) and show that toxic neurons only account for 2.5% to 24% of DPO's effects across models. Instead, DPO balances distributed activation shifts across all MLP neurons to create a net toxicity reduction. We attribute this reduction to four neuron groups, two aligned with reducing toxicity and two promoting anti-toxicity, whose combined effects replicate DPO across models. To further validate this understanding, we develop an activation editing method mimicking DPO through distributed shifts along a toxicity representation. This method outperforms DPO in reducing toxicity while preserving perplexity, without requiring any weight updates. Our work provides a mechanistic understanding of DPO and introduces an efficient, tuning-free alternative for safety fine-tuning.

cs.LG↗

arXiv2024

Improving In-Context Learning with Small Language Model Ensembles

Large language models (LLMs) have shown impressive capabilities across various tasks, but their performance on domain-specific tasks remains limited. While methods like retrieval augmented generation and fine-tuning can help to address this, they require significant resources. In-context learning (ICL) is a cheap and efficient alternative but cannot match the accuracies of advanced methods. We present Ensemble SuperICL, a novel approach that enhances ICL by leveraging the expertise of multiple fine-tuned small language models (SLMs). Ensemble SuperICL achieves state of the art (SoTA) results on several natural language understanding benchmarks. Additionally, we test it on a medical-domain labelling task and showcase its practicality by using off-the-shelf SLMs fine-tuned on a general language task, achieving superior accuracy in large-scale data labelling compared to all baselines. Finally, we conduct an ablation study and sensitivity analyses to elucidate the underlying mechanism of Ensemble SuperICL. Our research contributes to the growing demand for efficient domain specialisation methods in LLMs, offering a cheap and effective method for practitioners.

cs.CL↗

arXiv2024

Combining Hough Transform and Deep Learning Approaches to Reconstruct ECG Signals From Printouts

This work presents our team's (SignalSavants) winning contribution to the 2024 George B. Moody PhysioNet Challenge. The Challenge had two goals: reconstruct ECG signals from printouts and classify them for cardiac diseases. Our focus was the first task. Despite many ECGs being digitally recorded today, paper ECGs remain common throughout the world. Digitising them could help build more diverse datasets and enable automated analyses. However, the presence of varying recording standards and poor image quality requires a data-centric approach for developing robust models that can generalise effectively. Our approach combines the creation of a diverse training set, Hough transform to rotate images, a U-Net based segmentation model to identify individual signals, and mask vectorisation to reconstruct the signals. We assessed the performance of our models using the 10-fold stratified cross-validation (CV) split of 21,799 recordings proposed by the PTB-XL dataset. On the digitisation task, our model achieved an average CV signal-to-noise ratio of 17.02 and an official Challenge score of 12.15 on the hidden set, securing first place in the competition. Our study shows the challenges of building robust, generalisable, digitisation approaches. Such models require large amounts of resources (data, time, and computational power) but have great potential in diversifying the data available.

cs.LG↗