Large Language Models

Use argumentative reasoning to make the implicit content of hate speech explicit.

Evaluate whether large language models can perform selective rationalization through prompting.

Train text classifiers from annotation guidelines alone, without class labels.

Detect and classify unfair clauses in Terms of Service and Privacy Policies.

A community roadmap for evaluating Italian LLMs: what to test, how to test it, where to find data, and how to keep benchmarking sustainable.

A new corpus of 30 Italian privacy policies shows that BERT models beat LLMs at flagging vague data clauses and that resources transfer across languages.

Choosing few-shot examples per query by similarity lets LLMs mine legal arguments in EU court rulings as well as or better than expert-chosen examples.

A fine-tuned Llama 3 writes English grammar multiple-choice exercises without predefined constraints, and a rule-based check of their structure agrees with a human expert.

TWOLAR distills the passage ranking skill of ChatGPT into a Flan-T5 reranker, which matches far larger LLM rerankers on standard search benchmarks.