5 papers
Used Car Salesbots? Honesty and Credulity of LLMs as Bargaining Agents under Partial Information
Antonio Valerio Miceli-Barone, Vaishak Belle, Shay B. Cohen
In this work we study agents in simulated bargaining scenarios, where a buyer and a seller communicate through a text channel and attempt to negotiate mutually beneficial trades, u…
Improving LLM Code Reasoning via Semantic Equivalence Self-Play with Formal Verification
Antonio Valerio Miceli Barone, Poon Tsz Nok
We introduce a self-play framework for semantic equivalence in Haskell, utilizing formal verification to guide adversarial training between a generator and an evaluator. The framew…
Conversational Code Generation: a Case Study of Designing a Dialogue System for Generating Driving Scenarios for Testing Autonomous Vehicles
Rimvydas Rubavicius, Antonio Valerio Miceli-Barone, Alex Lascarides +1
Cyber-physical systems like autonomous vehicles are tested in simulation before deployment, using domain-specific programs for scenario specification. To aid the testing of autonom…
Program Semantic Inequivalence Game with Large Language Models
Antonio Valerio Miceli-Barone, Vaishak Belle, Ali Payani
Large Language Models (LLMs) can achieve strong performance on everyday coding tasks, but they can fail on complex tasks that require non-trivial reasoning about program semantics.…
A test suite of prompt injection attacks for LLM-based machine translation
Antonio Valerio Miceli-Barone, Zhifan Sun
LLM-based NLP systems typically work by embedding their input data into prompt templates which contain instructions and/or in-context examples, creating queries which are submitted…