Massive and diverse web data are increasingly vital for government disaster response, as demonstrated by the 2022 floods in New South Wales (NSW), Australia. This study examines how X (formerly Twitter) and public inquiry submissions provide insights into public behaviour during crises. We analyse more than 55,000 flood-related tweets and 1,450 submissions to identify behavioural patterns during extreme weather events. While social media posts are short and fragmented, inquiry submissions are detailed, multi-page documents offering structured insights. Our methodology integrates Latent Dirichlet Allocation (LDA) for topic modelling with Large Language Models (LLMs) to enhance semantic understanding. LDA reveals distinct opinions and geographic patterns, while LLMs improve filtering by identifying flood-relevant tweets using public submissions as a reference. This Relevance Index method reduces noise and prioritizes actionable content, improving situ-ational awareness for emergency responders. By combining these complementary data streams, our approach introduces a novel AI-driven method to refine crisis-related social media content, improve real-time disaster response, and inform long-term resilience planning.

Creativity has long been considered one of the most difficult aspect of human intelligence for AI to mimic. However, the rise of Large Language Models (LLMs), like ChatGPT, has raised questions about whether AI can match or even surpass human creativity. We present CREATIVITY INDEX as the first step to quantify the linguistic creativity of a text by reconstructing it from existing text snippets on the web. CREATIVITY INDEX is motivated by the hypothesis that the seemingly remarkable creativity of LLMs may be attributable in large part to the creativity of human-written texts on the web. To compute CREATIVITY INDEX efficiently, we introduce DJ SEARCH, a novel dynamic programming algorithm that can search verbatim and near-verbatim matches of text snippets from a given document against the web. Experiments reveal that the CREATIVITY INDEX of professional human authors is on average 66.2% higher than that of LLMs, and that alignment reduces the CREATIVITY INDEX of LLMs by an average of 30.1%. In addition, we find that distinguished authors like Hemingway exhibit measurably higher CREATIVITY INDEX compared to other human writers. Finally, we demonstrate that CREATIVITY INDEX can be used as a surprisingly effective criterion for zero-shot machine text detection, surpassing the strongest existing zero-shot system, DetectGPT, by a significant margin of 30.2%, and even outperforming the strongest supervised system, GhostBuster, in five out of six domains.

Text Classification (TC) stands as a cornerstone within the realm of Natural Language Processing (NLP), particularly when viewed through the lens of computer science and engineering. The past decade has seen deep learning revolutionize TC, propelling advancements in text retrieval, categorization, information extraction, and summarization. The scholarly literature is rich with datasets, models, and evaluation criteria, with English being the predominant language of focus, despite studies involving Arabic, Chinese, Hindi, and others. The efficacy of TC models relies heavily on their ability to capture intricate textual relationships and nonlinear correlations, necessitating a comprehensive examination of the entire TC pipeline. This monograph provides an in-depth exploration of the TC pipeline, with a particular emphasis on evaluating the impact of each component on the overall performance of TC models. The pipeline includes state-of-the-art datasets, text preprocessing techniques, text representation methods, classification models, evaluation metrics, current results and future trends. Each chapter meticulously examines these stages, presenting technical innovations and significant recent findings. The work critically assesses various classification strategies, offering comparative analyses, examples, case studies, and experimental evaluations. These contributions extend beyond a typical survey, providing a detailed and insightful exploration of TC.

We present SuffixDecoding, a novel model-free approach to accelerating large language model (LLM) inference through speculative decoding. Unlike existing methods that rely on draft models or specialized decoding heads, SuffixDecoding leverages suffix trees built from previously generated outputs to efficiently predict candidate token sequences. Our approach enables flexible tree-structured speculation without the overhead of maintaining and orchestrating additional models. SuffixDecoding builds and dynamically updates suffix trees to capture patterns in the generated text, using them to construct speculation trees through a principled scoring mechanism based on empirical token frequencies. SuffixDecoding requires only CPU memory which is plentiful and underutilized on typical LLM serving nodes. We demonstrate that SuffixDecoding achieves competitive speedups compared to model-based approaches across diverse workloads including open-domain chat, code generation, and text-to-SQL tasks. For open-ended chat and code generation tasks, SuffixDecoding achieves up to $1.4\times$ higher output throughput than SpecInfer and up to $1.1\times$ lower time-per-token (TPOT) latency. For a proprietary multi-LLM text-to-SQL application, SuffixDecoding achieves up to $2.9\times$ higher output throughput and $3\times$ lower latency than speculative decoding. Our evaluation shows that SuffixDecoding maintains high acceptance rates even with small reference corpora of 256 examples, while continuing to improve performance as more historical outputs are incorporated.

Recent large language models (LLMs) have excelled across a wide range of tasks, but their use in high-stakes and compute-limited settings has intensified the demand for interpretability and efficiency. We address this need by proposing Induction-head ngram models (Induction-Gram), a method that builds an efficient, interpretable LM by bolstering modern ngram models with a hand-engineered "induction head". This induction head uses a custom neural similarity metric to efficiently search the model's input context for potential next-word completions. This process enables Induction-Gram to provide ngram-level grounding for each generated token. Moreover, experiments show that this simple method significantly improves next-word prediction over baseline interpretable models (up to 26%p) and can be used to speed up LLM inference for large models through speculative decoding. We further study Induction-Gram in a natural-language neuroscience setting, where the goal is to predict the next fMRI response in a sequence. It again provides a significant improvement over interpretable models (20% relative increase in the correlation of predicted fMRI responses), potentially enabling deeper scientific investigation of language selectivity in the brain. The code is available at https://github.com/ejkim47/induction-gram.

Large Language Models (LLMs) perform outstandingly in various downstream tasks, and the use of the Retrieval-Augmented Generation (RAG) architecture has been shown to improve performance for legal question answering (Nuruzzaman and Hussain, 2020; Louis et al., 2024). However, there are limited applications in insurance questions-answering, a specific type of legal document. This paper introduces two corpora: the Quebec Automobile Insurance Expertise Reference Corpus and a set of 82 Expert Answers to Layperson Automobile Insurance Questions. Our study leverages both corpora to automatically and manually assess a GPT4-o, a state-of-the-art LLM, to answer Quebec automobile insurance questions. Our results demonstrate that, on average, using our expertise reference corpus generates better responses on both automatic and manual evaluation metrics. However, they also highlight that LLM QA is unreliable enough for mass utilization in critical areas. Indeed, our results show that between 5% to 13% of answered questions include a false statement that could lead to customer misunderstanding.

In this project, we demonstrate that phoneme-based models for speech processing can achieve strong crosslinguistic generalizability to unseen languages. We curated the IPAPACK, a massively multilingual speech corpora with phonemic transcriptions, encompassing more than 115 languages from diverse language families, selectively checked by linguists. Based on the IPAPACK, we propose CLAP-IPA, a multi-lingual phoneme-speech contrastive embedding model capable of open-vocabulary matching between arbitrary speech signals and phonemic sequences. The proposed model was tested on 95 unseen languages, showing strong generalizability across languages. Temporal alignments between phonemes and speech signals also emerged from contrastive training, enabling zeroshot forced alignment in unseen languages. We further introduced a neural forced aligner IPA-ALIGNER by finetuning CLAP-IPA with the Forward-Sum loss to learn better phone-to-audio alignment. Evaluation results suggest that IPA-ALIGNER can generalize to unseen languages without adaptation.

Temporal expression identification is crucial for understanding texts written in natural language. Although highly effective systems such as HeidelTime exist, their limited runtime performance hampers adoption in large-scale applications and production environments. In this paper, we introduce the TEI2GO models, matching HeidelTime's effectiveness but with significantly improved runtime, supporting six languages, and achieving state-of-the-art results in four of them. To train the TEI2GO models, we used a combination of manually annotated reference corpus and developed ``Professor HeidelTime'', a comprehensive weakly labeled corpus of news texts annotated with HeidelTime. This corpus comprises a total of $138,069$ documents (over six languages) with $1,050,921$ temporal expressions, the largest open-source annotated dataset for temporal expression identification to date. By describing how the models were produced, we aim to encourage the research community to further explore, refine, and extend the set of models to additional languages and domains. Code, annotations, and models are openly available for community exploration and use. The models are conveniently on HuggingFace for seamless integration and application.

Social media platforms hold valuable insights, yet extracting essential information can be challenging. Traditional top-down approaches often struggle to capture critical signals in rapidly changing events. As global events evolve swiftly, social media narratives, including instances of disinformation, become significant sources of insights. To address the need for an inductive strategy, we explore a niche social media platform GAB and an established messaging service Telegram, to develop methodologies applicable on a broader scale. This study investigates narrative evolution on these platforms using quantitative corpus-based discourse analysis techniques. Our approach is a novel mode to study multiple social media domains to distil key information which may be obscured otherwise, allowing for useful and actionable insights. The paper details the technical and methodological aspects of gathering and preprocessing GAB and Telegram data for a keyness (Log Ratio) metric analysis, identifying crucial nouns and verbs for deeper exploration. Empirically, this approach is applied to a case study of a well defined event that had global impact: the 2023 Wagner mutiny. The main findings are: (1) the time line can be deconstructed to provide useful data features allowing for improved interpretation; (2) a methodology is applied which provides a basis for generalization. The key contribution is an approach, that in some cases, provides the ability to capture the dynamic narrative shifts over time with elevated confidence. The approach can augment near-real-time assessment of key social movements, allowing for informed governance choices. This research is important because it lays out a useful methodology for time series relevant info-culling, which can enable proactive modes for positive social engagement.

Although deep language representations have become the dominant form of language featurization in recent years, in many settings it is important to understand a model's decision-making process. This necessitates not only an interpretable model but also interpretable features. In particular, language must be featurized in a way that is interpretable while still characterizing the original text well. We present SenteCon, a method for introducing human interpretability in deep language representations. Given a passage of text, SenteCon encodes the text as a layer of interpretable categories in which each dimension corresponds to the relevance of a specific category. Our empirical evaluations indicate that encoding language with SenteCon provides high-level interpretability at little to no cost to predictive performance on downstream tasks. Moreover, we find that SenteCon outperforms existing interpretable language representations with respect to both its downstream performance and its agreement with human characterizations of the text.