Understanding temporal relationships and accurately reconstructing the event timeline is important for case law analysis, compliance monitoring, and legal summarization. However, existing benchmarks lack specialized language evaluation, leaving a gap in understanding how LLMs handle event ordering in legal contexts. We introduce LexTime, a dataset designed to evaluate LLMs’ event ordering capabilities in legal language, consisting of 512 instances from U.S. Federal Complaints with annotated event pairs and their temporal relations. Our findings show that (1) LLMs are more accurate on legal event ordering than on narrative texts (up to +10.5%); (2) longer input contexts and implicit events boost accuracy, reaching 80.8% for implicit-explicit event pairs; (3) legal linguistic complexities and nested clauses remain a challenge. While performance is promising, specific features of legal texts remain a bottleneck for legal temporal event reasoning, and we propose concrete modeling directions to better address them.

Anomaly detection (AD), also known as Outlier Detection, is a longstanding problem in machine learning, which has recently been applied to text data. In these datasets, a textual anomaly is a part of the text that does not fit the overall topic of the text. Some recent approaches to textual AD have used transformer models, achieving positive results but with trade-offs in pre-training time and inflexibility with respect to new domains. Others have used linear models which are fast and more flexible but not always competitive on certain datasets. We introduce a new approach based on Large Pre-trained Language Models in three modalities. Our findings indicate that LLMs beat baselines when AD is presented as an imbalanced classification problem regardless of the concentration of anomalous samples. However, their performance is markedly worse on unsupervised AD, suggesting that the concept of “anomaly” may somehow elude the LLM reasoning process.

Conversational derailment — when online discussions stray from their intended topics due to toxic or inappropriate remarks — is a common issue on online platforms. These derailments can have negative impacts on users and the online community. While previous work has focused on post hoc identification of toxic content, recent efforts emphasize proactive prediction of derailments before they occur, enabling early moderation. However, forecasting derailment is difficult due to the context-dependent emergence of toxicity and the need for timely alerts. We prompt pre-trained large language models (LLMs) to predict conversational derailment without task-specific fine-tuning. We compare a range of prompting strategies, including chain-of-thought reasoning (CoT) and few-shot exemplars, across small and large scale models, and evaluate their performance and inference-cost trade-offs on derailment benchmarks. Our experiments show that the best prompting configuration attains state-of-the-art performance, and forecasts derailments earlier than existing approaches. These results demonstrate that LLMs, even without fine-tuning, can serve as an effective tool for proactive conversational moderation.