Introduces EURO-5K dataset from 136 EU acts and benchmarks full fine-tuning vs QLoRA for BERT and LLM models on reporting obligation extraction, reporting 0.89 F1 with limited gains from legal pretraining except under parameter-efficient adaptation.
Deontic ambiguities in legal reasoning
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
PolicyGuard is a neuro-symbolic framework that formalizes policies as typed relational logic rules and atom-level LLM questions, then uses symbolic evaluation for explicit compliance checking on documents such as NDAs.
A survey of RLM use in 28 disciplines reveals uneven adoption and introduces a maturity assessment framework showing larger gaps when limited to public resources.
Internal LLM artifacts can be used to build classifiers that identify incorrect predictions on legal classification tasks.
The authors define Deontic Argumentation Theory and introduce a new semantics supporting weak permission, unlike grounded semantics in obligation conflicts.
citing papers explorer
-
EURO-5K: When Does Domain Pretraining Matter? Benchmarking Transformers for EU Reporting Obligation Extraction
Introduces EURO-5K dataset from 136 EU acts and benchmarks full fine-tuning vs QLoRA for BERT and LLM models on reporting obligation extraction, reporting 0.89 F1 with limited gains from legal pretraining except under parameter-efficient adaptation.
-
PolicyGuard: From Organizational Policies to Neuro-SymbolicCompliance Review Engines
PolicyGuard is a neuro-symbolic framework that formalizes policies as typed relational logic rules and atom-level LLM questions, then uses symbolic evaluation for explicit compliance checking on documents such as NDAs.
-
Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches
A survey of RLM use in 28 disciplines reveals uneven adoption and introduces a maturity assessment framework showing larger gaps when limited to public resources.
-
Peeking Inside LLMs: Leveraging Internal Artifacts of LLMs for Enhancing Reliability in Legal Classification
Internal LLM artifacts can be used to build classifiers that identify incorrect predictions on legal classification tasks.