Training data detection is critical for enforcing copyright and data licensing, as Large Language Models (LLM) are trained on massive text corpora scraped from the internet. We present SPECTRA, a watermarking approach that makes training data reliably detectable even when it comprises less than 0.001% of the training corpus. SPECTRA works by paraphrasing text using an LLM and assigning a score based on how likely each paraphrase is, according to a separate scoring model. A paraphrase is chosen so that its score closely matches that of the original text, to avoid introducing any distribution shifts. To test whether a suspect model has been trained on the watermarked data, we compare its token probabilities against those of the scoring model. We demonstrate that SPECTRA achieves a consistent p-value gap of over nine orders of magnitude when detecting data used for training versus data not used for training, which is greater than all baselines tested. SPECTRA equips data owners with a scalable, deploy‑before‑release watermark that survives even large‑scale LLM training.

Due to their ability to process long and complex contexts, LLMs can offer key benefits to the Legal domain, but their adoption has been hindered by their tendency to generate unfaithful, ungrounded, or hallucinatory outputs. While Retrieval-Augmented Generation offers a promising solution by grounding generations in external knowledge, it offers no guarantee that the provided context will be effectively integrated. To address this, context-aware decoding strategies have been proposed to amplify the influence of relevant context, but they usually do not explicitly enforce faithfulness to the context. In this work, we introduce Confidence-guided Copy-based Decoding for Legal Text Generation (CoCoLex)-a decoding strategy that dynamically interpolates the model produced vocabulary distribution with a distribution derived based on copying from the context. CoCoLex encourages direct copying based on the model's confidence, ensuring greater fidelity to the source. Experimental results on five legal benchmarks demonstrate that CoCoLex outperforms existing context-aware decoding methods, particularly in long-form generation tasks.

Arturo Oncevay, Charese Smiley, Xiaomo Liu. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

In dental cone-beam computed tomography (CBCT), metal implants can cause metal artifacts, affecting image quality and the final medical diagnosis. To reduce the impact of metal artifacts, our proposed metal artifacts reduction (MAR) method takes a novel approach by integrating CBCT data with intraoral optical scanning data, utilizing information from these two different modalities to correct metal artifacts in the projection domain using a guided-diffusion model. The intraoral optical scanning data provides a more accurate generation domain for the diffusion model. We have proposed a multi-channel generation method in the training and generation stage of the diffusion model, considering the physical mechanism of CBCT, to ensure the consistency of the diffusion model generation. In this paper, we present experimental results that convincingly demonstrate the feasibility and efficacy of our approach, which introduces intraoral optical scanning data into the analysis and processing of projection domain data using the diffusion model for the first time, and modifies the diffusion model to better adapt to the physical model of CBCT.

Dongsheng Wang, Natraj Raman, Mathieu Sibue, Zhiqiang Ma, Petr Babkin, Simerjot Kaur, Yulong Pei, Armineh Nourbakhsh, Xiaomo Liu. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Natural language processing (NLP) technologies have been widely applied in business domains such as e-commerce and customer service, but their adoption in the financial sector has been constrained by industry-specific performance standards and regulatory restrictions. This challenge has created new opportunities for core research in related areas. Recent advancements in NLP, such as the advent of large language models, has encouraged adoption in the finance sector. However, compared to other domains, finance has stricter requirements for robustness, explainability, and generalizability. Given this background, we propose to organize the first Robust NLP for Finance (RobustFin) workshop at KDD '23 to encourage the study of and research on robustness and explainability technologies with regard to financial NLP. The goal of the workshop is to extend the applications of NLP in finance, while motivating further research in robust NLP.

Knowledge discovery from unstructured data, including business documents, web content, and news articles, has been a key AI challenge for the financial services industry. Comprehending these corpora and discovering knowledge from them, which could be textual, tabular, or graphic, are the cornerstone of supporting business decisions in the financial services domain, where information retrieval and content analysis techniques are of fundamental importance. We propose a workshop on knowledge discovery from unstructured data in financial services at SIGIR 2023 to highlight the current and emerging opportunities, invite original research, and prompt success sharing between researchers.

In the financial services industry, it is crucial for analysts to constantly monitor and stay informed on the latest developments of their portfolio of companies. This ensures that analysts are up-to-date in their analysis and provide highly credible and timely insights. Currently, analysts receive news alerts through manually created news alert subscriptions that are often noisy and difficult to manage. The manual review process is time-consuming and error-prone. We demonstrate Discovery News, a framework for an automated news recommender system for financial analysis at S&P's Global Ratings. This system includes the automated ingestion, relevancy, clustering, and ranking of news. The proposed framework is adaptable to any form of input news data and can seamlessly integrate with other data used for analysis like financial data.

To deal with the sheer volume of information and gain competitive advantage, the news industry has started to explore and invest in news automation. In this paper, we present Reuters Tracer, a system that automates end-to-end news production using Twitter data. It is capable of detecting, classifying, annotating, and disseminating news in real time for Reuters journalists without manual intervention. In contrast to other similar systems, Tracer is topic and domain agnostic. It has a bottom-up approach to news detection, and does not rely on a predefined set of sources or subjects. Instead, it identifies emerging conversations from 12+ million tweets per day and selects those that are news-like. Then, it contextualizes each story by adding a summary and a topic to it, estimating its newsworthiness, veracity, novelty, and scope, and geotags it. Designing algorithms to generate news that meets the standards of Reuters journalists in accuracy and timeliness is quite challenging. But Tracer is able to achieve competitive precision, recall, timeliness, and veracity on news detection and delivery. In this paper, we reveal our key algorithm designs and evaluations that helped us achieve this goal, and lessons learned along the way.

In this paper, we present a new approach for detecting novel events from social media, specially Twitter, at real-time. An event is usually defined by who, what, where and when, and an event tweet usually contains terms corresponding to these aspects. To exploit this information, we propose a method that incorporates simple semantics by splitting the tweet term space into groups of terms that have the meaning of the same type. These groups are called semantic categories (classes) and each reflects one or more event aspects. The semantic classes include named entity, mention, location, hashtag, verb, noun and embedded link. To group tweets talking about the same event into the same cluster, similarity measuring is conducted by calculating class-wise similarity and then aggregating them together. Users of a real-time event detection system are usually only interested in novel (new) events, which are happening now or just happened a short time ago. To fulfill this requirement, a temporal identification module is used to filter out event clusters that are about old stories. The clustering module also computes a novelty score for each event cluster, which reflects how novel the event is, compared to previous events. We evaluated our event detection method using multiple quality metrics and a large-scale event corpus having millions of tweets. The experiment results show that the proposed online event detection method achieves the state-of-the-art performance. Our experiment also shows that the temporal identification module can effectively detect old events.

Two of the major problems in social media message classification are the data sparseness issue and the high degree of lexical variation. Paraphrases, or synonyms, are alternative ways of expressing the same meaning using different lexical variations. In this study, we try to use paraphrases to improve tweet topic classification performance. We explored two approaches to generating paraphrases, WordNet, which is a lexical database grouping English words into sets of synonyms, and word embeddings, which are learned from millions of tweets and billions of words. Our experiment shows that using paraphrases can improve the topic classification task, and the word embedding approach outperforms the WordNet method. To our knowledge, this is the first study exploiting paraphrases for tweet classification.

Classifying tweets into topic categories is necessary and important for many applications, since tweets are about a variety of topics and users are only interested in certain topical areas. Many tweet classification approaches fail to achieve high accuracy due to data sparseness issue. Tweet, as a special type of short text, in additional to its text, also has other metadata that can be used to enrich its context, such as user name, mention, hashtag and embedded link. In this demonstration, we present TweetSift, an efficient and effective real time tweet topic classifier. TweetSift exploits external tweet-specific entity knowledge to provide more topical context for a tweet, and integrates them with topic enhanced word embeddings for topic classification. The demonstration will show how TweetSift works and how it is incorporated with our social media event detection system.

In this paper, we present a new approach of recommending hashtags for tweets. It uses Learning to Rank algorithm to incorporate features built from topic enhanced word embeddings, tweet entity data, hashtag frequency, hashtag temporal data and tweet URL domain information. The experiments using millions of tweets and hashtags show that the proposed approach outperforms the three baseline methods -- the LDA topic, the tf.idf based and the general word embedding approaches.

News professionals are facing the challenge of discovering news from more diverse and unreliable information in the age of social media. More and more news events break on social media first and are picked up by news media subsequently. The recent Brussels attack is such an example. At Reuters, a global news agency, we have observed the necessity of providing a more effective tool that can help our journalists to quickly discover news on social media, verify them and then inform the public.

Previous studies have used many manually identified features and word embeddings for tweet sentiment classification. In this paper, we propose a new approach, which incorporates sentiment-specific word embeddings (SSWE) and a weighted text feature model (WTFM). WTFM produces features based on text negation, tf.idf weighting scheme, and a Rocchio text classification method. Compared to other tweet sentiment feature generation approaches, WTFM is easy to build, simple, yet effective. Experiments show that the proposed approach outperforms the two state-of-the-art tweet sentiment classification methods, SSWE and National Research Council Canada's (NRC) model.

Many classification tasks on short text, such as tweet, fail to achieve high accuracy due to data sparseness. One approach to solving this problem is to enrich the context of data by using external data sources, or distributed language representations trained on huge amount of data. In this paper, we present several tweet topic classification methods by exploiting different types of data: tweet text, tweet text plus entity knowledge base, word embeddings derived from tweet text, distributed representations of tweets, and topical word embeddings. The word embedding, topical word embedding and sentence representation models are generated from billions of words from tweets without supervision. To the best of our knowledge, this is the first study of applying distributed language representations to tweet topic classification task.

In this paper, we propose the first real time rumor debunking algorithm for Twitter. We use cues from 'wisdom of the crowds', that is, the aggregate 'common sense' and investigative journalism of Twitter users. We concentrate on identification of a rumor as an event that may comprise of one or more conflicting microblogs. We continue monitoring the rumor event and generate real time updates dynamically based on any additional information received. We show using real streaming data that it is possible, using our approach, to debunk rumors accurately and efficiently, often much faster than manual verification by professionals.

In this paper we present findings from a project that used topic modeling and associated techniques to chart the emergence and growth of research topics in engineering education research over 9 years, from 2000-2008. As a field engineering education research has undergone significant changes over the past decade. There has been an increase in the number of scholars and practitioners involved in the field, particularly those that are applying rigorous research principles to advance understanding of engineering education. In such a circumstance, it is important to understand the topics, approaches, and ideas that have caught the imagination of people in the community. Since this nature of work has not been done in relation to engineering education research, a significant part of the effort described here is innovative and exploratory in nature where different techniques were tested with the goal to collect a diversity of topics that are of interest to the community. We identify major categories of topics and primary topics of interest to the community. We also identify a lack of engagement with theoretical and analytical ideas as an area of concern.