This paper explores whether enhancing temporal reasoning capabilities in Large Language Models (LLMs) can improve the quality of timeline summarization, the task of summarising long texts containing sequences of events, particularly social media threads . We introduce \textit{NarrativeReason}, a novel dataset focused on temporal relationships among sequential events within narratives, distinguishing it from existing temporal reasoning datasets that primarily address pair-wise event relationships. Our approach then combines temporal reasoning with timeline summarization through a knowledge distillation framework, where we first fine-tune a teacher model on temporal reasoning tasks and then distill this knowledge into a student model while simultaneously training it for the task of timeline summarization. Experimental results demonstrate that our model achieves superior performance on mental health-related timeline summarization tasks, which involve long social media threads with repetitions of events and a mix of emotions, highlighting the importance of leveraging temporal reasoning to improve timeline summarisation.

The intersection of chemistry and Artificial Intelligence (AI) is an active area of research focused on accelerating scientific discovery. While using large language models (LLMs) with scientific modalities has shown potential, there are significant challenges to address, such as improving training efficiency and dealing with the out-of-distribution problem. Focussing on the task of automated language-molecule translation, we are the first to use state-of-the art (SOTA) human-centric optimisation algorithms in the cross-modal setting, successfully aligning cross-language-molecule modals. We empirically show that we can augment the capabilities of scientific LLMs without the need for extensive data or large models. We conduct experiments using only 10% of the available data to mitigate memorisation effects associated with training large models on extensive datasets. We achieve significant performance gains, surpassing the best benchmark model trained on extensive in-distribution data by a large margin and reach new SOTA levels. Additionally we are the first to propose employing non-linear fusion for mixing cross-modal LLMs which further boosts performance gains without increasing training costs or data needs. Finally, we introduce a fine-grained, domain-agnostic evaluation method to assess hallucination in LLMs and promote responsible use.

The reasoning capabilities of LLMs are currently hotly debated. We examine the issue from the perspective of claim/rumour verification. We propose the first logical reasoning framework designed to break down any claim or rumor paired with evidence into the atomic reasoning steps necessary for verification. Based on our framework, we curate two annotated collections of such claim/evidence pairs: a synthetic dataset from Wikipedia and a real-world set stemming from rumours circulating on Twitter. We use them to evaluate the reasoning capabilities of GPT-3.5-Turbo and GPT-4 (hereinafter referred to as ChatGPT) within the context of our framework, providing a thorough analysis. Our results show that ChatGPT struggles in abductive reasoning, although this can be somewhat mitigated by using manual Chain of Thought (CoT) as opposed to Zero Shot (ZS) and ZS CoT approaches. Our study contributes to the growing body of research suggesting that ChatGPT's reasoning processes are unlikely to mirror human-like reasoning, and that LLMs need to be more rigorously evaluated in order to distinguish between hype and actual capabilities, especially in high stake real-world tasks such as claim verification.

We present an open-source, pip installable toolkit, Sig-Networks, the first of its kind for longitudinal language modelling. A central focus is the incorporation of Signature-based Neural Network models, which have recently shown success in temporal tasks. We apply and extend published research providing a full suite of signature-based models. Their components can be used as PyTorch building blocks in future architectures. Sig-Networks enables task-agnostic dataset plug-in, seamless pre-processing for sequential data, parameter flexibility, automated tuning across a range of models. We examine signature networks under three different NLP tasks of varying temporal granularity: counselling conversations, rumour stance switch and mood changes in social media threads, showing SOTA performance in all three, and provide guidance for future tasks. We release the Toolkit as a PyTorch package with an introductory video, Git repositories for preprocessing and modelling including sample notebooks on the modeled NLP tasks.

We introduce the new task of clinically meaningful summarisation of social media user timelines, appropriate for mental health monitoring. We develop a novel approach for unsupervised abstractive summarisation that produces a two-layer summary consisting of both high-level information, covering aspects useful to clinical experts, as well as accompanying time sensitive evidence from a user's social media timeline. A key methodological novelty comes from the timeline summarisation component based on a version of hierarchical variational autoencoder (VAE) adapted to represent long texts and guided by LLM-annotated key phrases. The resulting timeline summary is input into a LLM (LLaMA-2) to produce the final summary containing both the high level information, obtained through instruction prompting, as well as corresponding evidence from the user's timeline. We assess the summaries generated by our novel architecture via automatic evaluation against expert written summaries and via human evaluation with clinical experts, showing that timeline summarisation by TH-VAE results in logically coherent summaries rich in clinical utility and superior to LLM-only approaches in capturing changes over time.

The task of rumour verification in social media concerns assessing the veracity of a claim on the basis of conversation threads that result from it. While previous work has focused on predicting a veracity label, here we reformulate the task to generate model-centric, free-text explanations of a rumour's veracity. We follow an unsupervised approach by first utilising post-hoc explainability methods to score the most important posts within a thread and then we use these posts to generate informative explanatory summaries by employing template-guided summarisation. To evaluate the informativeness of the explanatory summaries, we exploit the few-shot learning capabilities of a large language model (LLM). Our experiments show that LLMs can have similar agreement to humans in evaluating summaries. Importantly, we show that explanatory abstractive summaries are more informative and better reflect the predicted rumour veracity than just using the highest ranking posts in the thread.

The task of assigning diagnostic ICD codes to patient hospital admissions is typically performed by expert human coders. Efforts towards automated ICD coding are dominated by supervised deep learning models. However, difficulties in learning to predict the large number of rare codes remain a barrier to adoption in clinical practice. In this work, we leverage off-the-shelf pre-trained generative large language models (LLMs) to develop a practical solution that is suitable for zero-shot and few-shot code assignment, with no need for further task-specific training. Unsupervised pre-training alone does not guarantee precise knowledge of the ICD ontology and specialist clinical coding task, therefore we frame the task as information extraction, providing a description of each coded concept and asking the model to retrieve related mentions. For efficiency, rather than iterating over all codes, we leverage the hierarchical nature of the ICD ontology to sparsely search for relevant codes.

Dementia is a neuro-degenerative disease affecting Early work in NLP for dementia relied on manual millions worldwide and is associated with cognitive engineered features based on specific lexical, decline, including language impairment (Forbes-acoustic and syntactic features stemming from description McKay and Venneri, 2005). Language dysfunction tasks (such as CTP), to detect linguistic may be difficult to detect in the early stages of dementia signs of cognitive decline (Fraser et al., 2016; Beltrami (Nestor et al., 2004); however, as the disease et al., 2018; Yeung et al., 2021). Recent progresses, a gradual decline of semantic knowledge work uses naive neural approaches to classify and ensues, and eventually, all linguistic functions analyse linguistic and acoustic characteristics so can be lost (Tang-Wai and Graham, 2008; Klimova as to either predict cognitive scores or achieve binary et al., 2015). Recognizing language disorders as classification of participants (Alzheimer's Disease prodromal symptoms in people with dementia may (AD) vs non-AD) (Karlekar et al., 2018; Balagopalan help with earlier diagnosis and improve disease et al., 2020; Nasreen et al., 2021b; Rohanian management.

The use of spontaneous language to derive appropriate digital markers has become an emergent, promising and non-intrusive method to diagnose and monitor dementia. Here we propose methods to capture language coherence as a cost-effective, human-interpretable digital marker for monitoring cognitive changes in people with dementia. We introduce a novel task to learn the temporal logical consistency of utterances in short transcribed narratives and investigate a range of neural approaches. We compare such language coherence patterns between people with dementia and healthy controls and conduct a longitudinal evaluation against three clinical bio-markers to investigate the reliability of our proposed digital coherence marker. The coherence marker shows a significant difference between people with mild cognitive impairment, those with Alzheimer's Disease and healthy controls. Moreover our analysis shows high association between the coherence marker and the clinical bio-markers as well as generalisability potential to other related conditions.

There is increasing interest to work with user generated content in social media, especially textual posts over time. Currently there is no consistent way of segmenting user posts into timelines in a meaningful way that improves the quality and cost of manual annotation. Here we propose a set of methods for segmenting longitudinal user posts into timelines likely to contain interesting moments of change in a user's behaviour, based on their online posting activity. We also propose a novel framework for evaluating timelines and show its applicability in the context of two different social media datasets. Finally, we present a discussion of the linguistic content of highly ranked timelines.