AmirMohseni/modernbert-base-v3-primary-topic-user-len4096-seed42

ModernBERT-base for primary legal-topic classification

This checkpoint assigns a primary legal topic to conversations in which the user is seeking legal guidance. It is the second stage of the full-conversation ModernBERT-base cascade from the Legal Guidance in the Wild study. Input contains chronological user messages only; assistant messages are excluded. The first-stage detector is modernbert-base-v3-seeks-guidance-user-len4096-seed42.

This is a research classifier, not a legal-advice system. Its topic prediction must not be treated as a determination of jurisdiction, rights, or legal merit.

Labels

The 14 labels are: FAMILY_AND_ESTATES, HOUSING_AND_PROPERTY, EMPLOYMENT_AND_LABOR, IMMIGRATION_AND_CITIZENSHIP, CRIMINAL_LAW, TAX_LAW, CONSUMER_AND_PERSONAL_FINANCE, BUSINESS_AND_COMMERCIAL, TORTS_AND_CIVIL_LIABILITY, GOVERNMENT_AND_ADMINISTRATIVE, CIVIL_RIGHTS_AND_CONSTITUTIONAL, DATA_PRIVACY_AND_TECHNOLOGY, INTELLECTUAL_PROPERTY, and OTHER. The exact ID mapping is stored in config.json.

Data

• Dataset: AmirMohseni/WildChat-Legal-Classification-V3-Hierarchical
• Requested revision: main (latest at run time)
• Train fingerprint: 6ba4c2696e889276
• Validation fingerprint: 403fe118d76c8360
• Topic-stage train / validation rows: 750 / 134 guidance-positive conversations
• Input mode: chronological user messages only

Dataset access follows the linked repository's sharing settings. The fingerprints identify the exact loaded splits even if main later changes.

Training configuration

Setting	Value
Base model	answerdotai/ModernBERT-base
Maximum length	4096
Epochs	10
Learning rate	6e-05
Effective batch size	32
Weight decay	0.01
Class weighting	Yes
Seed	42
Hardware	NVIDIA A100-SXM4-40GB

The checkpoint was selected by silver-validation macro-F1.

Silver-validation results

Evaluation	Accuracy	Macro-F1
Conditional topic stage (N=134)	0.724	0.603
Full base cascade (15-way, N=290)	0.762	0.550

The paired first-stage guidance detector obtains 0.879 macro-F1 and 0.875 positive-class F1. These development results are not final adjudicated-gold estimates.

Inference

from transformers import AutoModelForSequenceClassification, AutoTokenizer

repo = "AmirMohseni/modernbert-base-v3-primary-topic-user-len4096-seed42"
tokenizer = AutoTokenizer.from_pretrained(repo)
model = AutoModelForSequenceClassification.from_pretrained(repo)

# Run only after the paired guidance detector predicts guidance-seeking.
inputs = tokenizer(user_only_conversation, return_tensors="pt", truncation=True,
                   max_length=4096)
topic_id = int(model(**inputs).logits.argmax(-1)[0])
topic = model.config.id2label[topic_id]

Limitations

The model was trained on English-language public LLM interaction logs with silver labels, one source, and one seed. Several topics have limited validation support, so macro-F1 is unstable and topic-specific errors can be substantial. Inputs beyond 4,096 tokens are truncated. The taxonomy is jurisdiction-agnostic and cannot substitute for legal triage by a qualified professional. Human review is required for consequential use.

Citation

Please cite the accompanying Legal Guidance in the Wild: How Users Seek Legal Help in Real-World LLM Conversations manuscript when it becomes available.