Roberto Navigli · page 2

29 papers in our library · 2006–2026 · page 2 of 2

Papers

The most cited first (OpenAlex and our library).

ReTraceQA: Evaluating Reasoning Traces of Small Language Models in Commonsense Question Answering (2026 · 1 citation)
Commonsense benchmarks usually score Small Language Models (SLMs) only on whether the final answer matches the gold label.
Truth or Mirage? Towards End-To-End Factuality Evaluation with LLM-O asis (2026 · 1 citation)
LLMs still hallucinate, and their fluent output makes such errors easy to miss. Existing factuality benchmarks tend to be limited to one domain or task (e.g., news or dialogue summarization), are too small to train evaluators, or reduce the problem to checking single claims, as FEVER does. The authors present…
Cultural and Knowledge Biases in LLMs through the Lens of Entity-Aware Machine Translation (2026)
LLMs translate fluently, but they know far less about entities rooted in underrepresented cultures. Earlier cultural MT work also treated all "cultural" entities as one group. The authors study this gap through entity-aware machine translation (EA-MT) and propose a three-tier scale of cultural specificity:
Mind the Language Gap: Assessing LLM Safety in Italian (2026)
Most LLM safety benchmarks are built in English and reach other languages through machine translation, which can introduce artifacts and miss cultural context.