---
license: apache-2.0
base_model: google/muril-base-cased
tags:
- autoscientist
- adaption
- hr
- grievance-routing
- intent-classification
- multilingual
- hindi
- punjabi
datasets:
- tojpaj/hr-grievance-multilingual-indic
language:
- hi
- pa
---

# Worker Grievance Routing Model (MuRIL, Hindi/Punjabi)

MuRIL fine-tuned for native Hindi/Punjabi workplace grievance intent
classification (wage_dispute/harassment_escalation/leave_pf_esi/
general). AutoScientist Challenge Part 2, HR category.

## Results

Accuracy 82.1%, Macro-F1 0.225 (held-out 20% split, 28 rows).

**Known limitation, disclosed honestly:** built without ULCA
registration to fit the deadline, using IndicCorpV2 general web text
instead of genuine worker grievances. `general` dominates (127/137
training rows); the three genuine grievance intents have too few
examples (1-5 each) for reliable classification. The
escalation-bypass safety design this idea was built around
(harassment_escalation + urgency=immediate -> hard-route to a human)
is documented but not meaningfully testable on this round's thin
urgency-label data (only 4 total). See the source project's
`PART2_SUBMISSION.md`.