Lattice AI Research

Research focus

Code Generation & Program Synthesis (2)Natural Language Processing (2)Eval Frameworks & Benchmarks (1)Distributed Systems & Hardware (1)

Frequent co-authors

Arslan Bisharat (2)Brian Ortiz (2)Eric Spencer (2)Khushboo Bhadauria (2)

Papers (2)

Jun 4, 2026

Loyola University ChicagoJun 4, 2026

Can LLMs Write Correct TLA+ Specifications? Evaluating Natural-Language-to-TLA+ Generation

LLMs struggle to produce reliable TLA+ specifications, achieving only 8.6% semantic correctness, which underscores the need for expert oversight in automated formal verification.

Arslan Bisharat, Brian Ortiz, Eric Spencer +5

Code Generation & Program Synthesis Eval Frameworks & Benchmarks Natural Language Processing

Loyola University ChicagoJun 4, 2026

TLA-Prover: Verifiable TLA+ Specification Synthesis via Preference-Optimized Low-Rank Adaptation

TLA-Prover triples the success rate of LLM-generated TLA+ specifications, transforming how we ensure correctness in distributed systems verification.

Eric Spencer, Arslan Bisharat, Brian Ortiz +5

Code Generation & Program Synthesis Distributed Systems & Hardware Natural Language Processing

TaiNing Wang

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)

Search

TaiNing Wang

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)