Amrit Gopinath

TextSentinels @ FinMMEval 2026 Task 2: Chronological Stabilization of a BM25-Grounded Multilingual Financial Question Answering Pipeline

TextSentinels @ FinMMEval 2026 Task 3: Multi-Asset Financial Decision Making Using Machine Learning and Financial Transformers

This paper presents the iterative technical evolution of the quantitative trading agent for the FinMMEval 2026 Task 3 challenge, detailing an initial baseline architecture that failed due to domain-blind lexical text processing and structural feature alignment anomalies, and detail the core feature innovation: a mathem...

TextSentinels @ FinMMEval 2026 Task 1: A Multilingual Routed Retrieval-Augmented System for Financial Multiple Choice Questions

The approach builds a shared FAISS retrieval index from the official public Task 1 Hugging Face release after normalizing heterogeneous dataset schemas into a unified multiple-choice format.

Vectorizing Classical Tamil: Representation Learning for Verse-Commentary Pairs

TF-IDF provides a strong no-training lexical retrieval baseline, alongside representation analyses and generation controls for the learned models, and one narrow result remains: the decoder-only model prefers authentic word order in 107 of 112 minimal-pair comparisons, but does not reproduce held-out commentary content...

A Declarative-Procedural Perspective on Expert Routing in Bilingual Mixture-of-Experts Language Models

Results suggest that interpretable linguistic organization emerges within MoE routing patterns even without sequential language exposure, and suggest that staged bilingual exposure reduces single-language dominance.

COVER: Identifiable Evaluation of Coalition Routing

COLD is an auditable measurement methodology, an evaluation contract that fixes a public information boundary, downstream stack G, and finite legal team family before outcomes are generated, which exposes selection headroom without manufacturing a routing win.