Building on their demonstrated ability to perform a variety of tasks, we investigate the application of large language models (LLMs) to enhance in-depth analytical reasoning within the context of intelligence analysis. Intelligence analysts typically work with massive dossiers to draw connections between seemingly unrelated entities, and uncover adversaries’ plans and motives. We explore if and how LLMs can be helpful to analysts for this task and develop an architecture to augment the capabilities of an LLM with a memory module called dynamic evidence trees (DETs) to develop and track multiple investigation threads. Through extensive experiments on multiple datasets, we highlight how LLMs, as-is, are still inadequate to support intelligence analysts and offer recommendations to improve LLMs for such intricate reasoning applications.

The neural boom that has sparked natural language processing (NLP) research throughout the last decade has similarly led to significant innovations in data-to-text (D2T) generation. This survey offers a consolidated view into the neural D2T paradigm with a structured examination of the approaches, benchmark datasets, and evaluation protocols. This survey draws boundaries separating D2T from the rest of the natural language generation (NLG) landscape, encompassing an up-to-date synthesis of the literature, and highlighting the stages of technological adoption from within and outside the greater NLG umbrella. With this holistic view, we highlight promising avenues for D2T research that focus not only on the design of linguistically capable systems but also on systems that exhibit fairness and accountability.

The field of Math-NLP has witnessed significant growth in recent years, motivated by the desire to expand LLM performance to the learning of non-linguistic notions (numerals, and subsequently, arithmetic reasoning).However, non-linguistic skill injection typically comes at a cost for LLMs: it leads to catastrophic forgetting of core linguistic skills, a consequence that often remains unaddressed in the literature.As Math-NLP has been able to create LLMs that can closely approximate the mathematical skills of a grade-schooler or the arithmetic reasoning skills of a calculator, the practicality of these models fail if they concomitantly shed their linguistic capabilities.In this work, we take a closer look into the phenomena of catastrophic forgetting as it pertains to LLMs and subsequently offer a novel framework for non-linguistic skill injection for LLMs based on information-theoretic interventions and skill-specific losses that enable the learning of strict arithmetic reasoning.Our model outperforms the state-of-the-art both on injected non-linguistic skills and on linguistic knowledge retention, and does so with a fraction of the non-linguistic training data (1/4) and zero additional synthetic linguistic training data.Our pre-trained models and experimentation codebases are hosted online 1 .

The task of generating rich and fluent narratives that aptly describe the characteristics, trends, and anomalies of time-series data is invaluable to the sciences (geology, meteorology, epidemiology) or finance (trades, stocks). The efforts for time-series narration hitherto are domain-specific and use predefined templates that offer consistency but lead to mechanical narratives. We present $\mathrm{T}^{3}$ (Time-series-To-Text), a domain-agnostic neural framework for time-series narration, that couples the representation of essential time-series elements in the form of a dense knowledge graph and the translation of said knowledge graph into rich and fluent narratives through the transfer-learning capabilities of PLMs (Pre-trained Language Models). To the best of our knowledge, $\mathrm{T}^{3}$ is the first investigation of the use of neural strategies for time-series narration. We showcase that $\mathrm{T}^{3}$ can improve the lexical diversity of the generated narratives by up to 65.38% while still maintaining grammatical integrity. The performance and practicality of $\mathrm{T}^{3}$ is further validated through an expert review $(n=21)$ where 76.2% of participating experts wary of auto-generated narratives favored $\mathrm{T}^{3}$ as a deployable system for time-series narration due to its rich and diverse narratives. Our code-base and the datasets used with detailed instructions for reproducibility is publicly hosted1.1https://github.com/Mandar-Sharma/TCube

Causality visualization can help people understand temporal chains of events, such as messages sent in a distributed system, cause and effect in a historical conflict, or the interplay between political actors over time. However, as the scale and complexity of these event sequences grows, even these visualizations can become overwhelming to use. In this paper, we propose the use of textual narratives as a data-driven storytelling method to augment causality visualization. We first propose a design space for how textual narratives can be used to describe causal data. We then present results from a crowdsourced user study where participants were asked to recover causality information from two causality visualizations-causal graphs and Hasse diagrams-with and without an associated textual narrative. Finally, we describe Causeworks, a causality visualization system for understanding how specific interventions influence a causal model. The system incorporates an automatic textual narrative mechanism based on our design space. We validate Causeworks through interviews with experts who used the system for understanding complex events.