7 papers
How the Dirty Set Moves: Characterizing Schedule Reuse in Incremental Sparse Matrix Multiplication
Hunter Horne, Eric Spencer, Alex Henningfield +1
Sparse matrices, in which most entries are zero, are central to scientific simulation, graph analytics and machine learning, and their multiplication with dense inputs is a core pa…
Evaluating Financial Sentiment in the Age of AI
Arslan Bisharat, Oudom Hean
Financial sentiment measures are widely used in empirical finance, but it remains unclear whether general-purpose large language models (LLMs) improve on existing finance-specific…
Strategies to Avoid Illegal Data Access
Muhammad Mubeen, Arslan Bisharat, Giri Anandhi
For companies of all sizes, data security is a top priority. The chance of unauthorized data access increases as technology develops. To prevent unwanted access to their data, busi…
TLA-Prover: Verifiable TLA+ Specification Synthesis via Preference-Optimized Low-Rank Adaptation
Eric Spencer, Arslan Bisharat, Brian Ortiz +6
TLA+ is a formal specification language for verifying distributed systems and safety-critical protocols. Large language models (LLMs) frequently produce TLA+ specifications that fa…
TLA+-Bench: An Execution-Grounded Benchmark and Dataset for Natural-Language to TLA Specification Generation
Arslan Bisharat, Eric Spencer, Brian Ortiz +8
Large language models increasingly write TLA formal specifications from natural-language descriptions, but progress is hard to measure: existing resources grade by resemblanc…
SPILLOVER: Measuring Cyberbullying NormPropagation on Social Media
Arslan Bisharat, Katelyn Skees, Mujtaba Nazari +5
While certain aspects of cyberbullying (CB) such as its factors and prevalence have been studied extensively, relatively little attention has been given to specifically how the agg…
Can LLMs Write Correct TLA+ Specifications? Evaluating Natural-Language-to-TLA+ Generation
Arslan Bisharat, Brian Ortiz, Eric Spencer +5
TLA+ has supported industrial verification at companies such as Amazon and Microsoft, yet writing correct TLA+ specifications from natural language still requires time and expertis…