Papers with PBT

2 papers
Teaching Models to Balance Resisting and Accepting Persuasion (2025.naacl-long)

Copied to clipboard

Challenge: Large language models (LLMs) are susceptible to persuasion, which can pose risks when faced with an adversarial interlocutor.
Approach: They propose a method to balance positive and negative persuasion by using recursive dialogue trees to train models to accept persulasion.
Outcome: The proposed model-based training improves resistance to misinformation and resilience to being challenged while also resulting in the best overall performance on multi-agent debates across two domains.
Beyond Superficial Tests: Adversarial Refinement for Reliable Property-Based Testing (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated remarkable proficiency in code generation, yet their application to Property-Based Testing (PBT) remains fraught with a superficiality gap.
Approach: They propose an agentic framework that hardens software properties through Adversarial Refinement.
Outcome: a new framework hardens software properties through Adversarial Refinement that detects and fixes bugs in top-tier libraries.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations