13 papers
EMPATH: A Multilingual Auditor-Judge Benchmark for Safety Evaluation of Emotional-Support Chatbots
Camilo Chacón Sartori
Safety benchmarks often buy scalability by fixing the prompt, the language, and the turn structure. For emotional-support chatbots, that bargain hides precisely where safety failur…
A Fixed-Budget, Cluster-Aware Standard for LLM-as-a-Judge Evaluation: A Multi-Hop RAG Stress Test
Camilo Chacón Sartori, José H. GarcÃa
Retrieval-augmented generation (RAG) systems are often compared by asking a large language model (LLM) judge which answer is better. For multi-hop RAG, this has become a measuremen…
Coherent Without Grounding, Grounded Without Success: Observability and Epistemic Failure
Camilo Chacón Sartori
When an agent can articulate why something works, we typically take this as evidence of genuine understanding. This presupposes that effective action and correct explanation covary…
GEAKG: Generative Executable Algorithm Knowledge Graphs
Camilo Chacón Sartori, José H. GarcÃa, Andrei Voicu Tomut +1
In the context of algorithms for problem solving, procedural knowledge -- the know-how of algorithm design and operator composition -- remains implicit in code, lost between runs,…
The Specification Gap: Coordination Failure Under Partial Knowledge in Code Agents
Camilo Chacón Sartori
When multiple LLM-based code agents independently implement parts of the same class, they must agree on shared internal representations, even when the specification leaves those ch…
Code World Models for Parameter Control in Evolutionary Algorithms
Camilo Chacón Sartori, Guillem RodrÃguez Corominas
Can an LLM learn how an optimizer behaves -- and use that knowledge to control it? We extend Code World Models (CWMs), LLM-synthesized Python programs that predict environment dyna…