Assessing the reasoning capabilities of large language models (LLMs) is susceptible to overestimation due to data exposure of evaluation benchmarks. We introduce a framework for producing linguistic reasoning problems that reduces the effect of memorisation in model performance estimates and apply this framework to develop LINGOLY-TOO, a challenging benchmark for linguistic reasoning. By developing orthographic templates, we dynamically obfuscate the writing systems of real languages to generate numerousquestion variations. These variations preserve the reasoning steps required for each solution while reducing the likelihood of specific problem instances appearing in model training data. Our experiments demonstrate that frontier models, including Claud 3.7 Sonnet, o1-preview and DeepSeek R1, struggle with advanced reasoning. Our analysis also shows that LLMs exhibit noticeable variance in accuracy across permutations of the same problem, and on average perform better on questions appearing in their original orthography. Our findings highlight the opaque nature of response generation in LLMs and provide evidence that prior data exposure contributes to over estimating the reasoning capabilities of frontier models.

Safety fine-tuning algorithms are widely used to reduce harmful outputs in language models, but how they achieve this remain unclear. Studying the Direct Preference Optimization (DPO) algorithm for toxicity reduction, current explanations claim that DPO achieves this by dampening the activations of toxic MLP neurons. However, through activation patching, we show that this explanation is incomplete. Projections onto a toxicity probe's direction show that only 4.9% of toxicity reduction comes from dampened toxic neurons. Instead, DPO reduces toxicity through distributed activation shifts across a majority of neurons, progressively shifting MLP layer outputs away from toxicity. These shifts accumulate across four neuron groups: two reducing toxicity and two promoting anti-toxicity. Activation patching validates the cumulative roles of these groups, where patching all identified groups effectively replicates DPO's effects. These findings illustrate DPO's mechanism: it reduces toxicity by accumulating small activation shifts across many neurons throughout the layers. Our findings provide new mechanistic insights into how safety fine-tuning reduces harmful outputs in language models.

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.

In this paper, we present the LingOly benchmark, a novel benchmark for advanced reasoning abilities in large language models. Using challenging Linguistic Olympiad puzzles, we evaluate (i) capabilities for in-context identification and generalisation of linguistic patterns in very low-resource or extinct languages, and (ii) abilities to follow complex task instructions. The LingOly benchmark covers more than 90 mostly low-resource languages, minimising issues of data contamination, and contains 1,133 problems across 6 formats and 5 levels of human difficulty. We assess performance with both direct accuracy and comparison to a no-context baseline to penalise memorisation. Scores from 11 state-of-the-art LLMs demonstrate the benchmark to be challenging, and models perform poorly on the higher difficulty problems. On harder problems, even the top model only achieved 38.7% accuracy, 24.7% improvement over the no-context baseline. Large closed models typically outperform open models, and in general, the higher resource the language, the better the scores. These results indicate, in absence of memorisation, true multi-step out-of-domain reasoning remains a challenge for current language models.

The use of unsupervised learning to identify patient subgroups has emerged as a potentially promising direction to improve the efficiency of Intensive Care Units (ICUs). By identifying subgroups of patients with similar levels of medical resource need, ICUs could be restructured into a collection of smaller subunits, each catering to a specific group. However, it is unclear whether common patient subgroups exist across different ICUs, which would determine whether ICU restructuring could be operationalised in a standardised manner. In this paper, we tested the hypothesis that common ICU patient subgroups exist by examining whether the results from one existing study generalise to a different dataset. We extracted 16 features representing medical resource need and used consensus clustering to derive patient subgroups, replicating the previous study. We found limited similarities between our results and those of the previous study, providing evidence against the hypothesis. Our findings imply that there is significant variation between ICUs; thus, a standardised restructuring approach is unlikely to be appropriate. Instead, potential efficiency gains might be greater when the number and nature of the subunits are tailored to each ICU individually.