Leslie Barrett

Apurv Verma, Satyapriya Krishna, Sebastian Gehrmann et al. · amazon-science, gatech

Creating secure and resilient applications with large language models (LLM) requires anticipating, adjusting to, and countering unforeseen threats. Red-teaming has emerged as a critical technique for identifying vulnerabilities in real-world LLM implementations. This paper presents a detailed threat model and provides a systematization of knowledge (SoK) of red-teaming attacks on LLMs. We develop a taxonomy of attacks based on the stages of the LLM development and deployment process and extract various insights from previous research. In addition, we compile methods for defense and practical red-teaming strategies for practitioners. By delineating prominent attack motifs and shedding light on various entry points, this paper provides a framework for improving the security and robustness of LLM-based systems.

Parisa Kordjamshidi, Samer Aslan, Madhavan Seshadri et al.

Recent advances in large language models (LLMs) have significantly enhanced automated legal reasoning. Yet, it remains unclear whether their performance reflects genuine legal reasoning ability or artifacts of data contamination. We present a comprehensive empirical study of tax law reasoning approaches and implement a contamination detection protocol to rigorously assess LLM reliability. We show that performance can be inflated by contamination. Building on this analysis, we conduct a systematic evaluation, comparing monolithic LLMs with hybrid systems that translate statutory text into formal representations and delegate inference to symbolic solvers. We build a novel test suite designed to probe generalization to unseen documents via case and rule variations. Our findings indicate that legal reasoning is inherently compositional and that neuro-symbolic frameworks offer a more reliable and robust foundation for legal AI, as well as improved generalization to unobserved situations.

Leslie Barrett, Michael W. Sherman

Hand-tagged training data is essential to many machine learning tasks. However, training data quality control has received little attention in the literature, despite data quality varying considerably with the tagging exercise. We propose methods to evaluate and enhance the quality of hand-tagged training data using statistical approaches to measure tagging consistency and agreement. We show that agreement metrics give more reliable results if recorded over multiple iterations of tagging, where declining variance in such recordings is an indicator of increasing data quality. We also show one way a tagging project can collect high-quality training data without requiring multiple tags for every work item, and that a tagger burn-in period may not be sufficient for minimizing tagger errors.

Claire Barale, Leslie Barrett, Vikram Sunil Bajaj et al.

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.

Paolo Pedinotti, Peter Baumann, Nathan Jessurun et al.

Large Language Models (LLMs) have rapidly reshaped financial NLP, enabling new tasks and driving a proliferation of datasets and diversification of data sources. Yet, this transformation has outpaced traditional surveys. In this paper, we present MetaGraph, a generalizable methodology for extracting knowledge graphs from scientific literature and analyzing them to obtain a structured, queryable view of research trends. We define an ontology for financial NLP research and apply an LLM-based extraction pipeline to 681 papers (2022-2025), enabling large-scale, data-driven analysis. MetaGraph reveals three key phases: early LLM adoption and task/dataset innovation; critical reflection on LLM limitations; and growing integration of peripheral techniques into modular systems. This structured view offers both practitioners and researchers a clear understanding of how financial NLP has evolved - highlighting emerging trends, shifting priorities, and methodological shifts-while also demonstrating a reusable approach for mapping scientific progress in other domains.