On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “stackexchange”

Ranking Clarification Questions via Natural Language Inferencecs.LG

The paper teaches machines to ask clarifying questions by applying NLI.

problem Teaching machines to ask clarifying questions for better comprehension.

method The approach is to use NLI to determine if a clarification question is about a missing piece of information in a post.

result The best model improved precision@1 by 40% and 60% over state-of-the-art baselines.

natural language inference clarification questions machine learning stackexchange nlp

2020-08-18abs ↗pdf ↗

Summaries as Centroids for Interpretable and Scalable Text Clusteringcs.CL

Text clustering method replaces centroids with summaries for interpretability and scalability.

problem Efficiently clustering text data while maintaining interpretability and scalability.

method k-NLPmeans and k-LLMmeans, which periodically replace numeric centroids with textual summaries.

result Consistently outperforms classical baselines and recent LLM-based clustering methods.

text clustering centroids summaries interpretability scalability

2025-02-12abs ↗pdf ↗

Rationalizing Text Matching: Learning Sparse Alignments via Optimal Transportcs.LG

Sparse text alignments learned via optimal transport improve model explainability.

problem Building self-explaining models by selecting relevant text pieces.

method Employing optimal transport to find minimal cost alignments, introducing constrained variants for sparsity.

result Sparse and interpretable alignments achieved, preserving prediction accuracy.

optimal transport sparse alignment text matching explainable AI self-explaining models

2020-05-27abs ↗pdf ↗

Adaptive Matching for Expert Systems with Uncertain Task Typescs.AI

A matching in a two-sided market often incurs an externality: a matched resource may become unavailable to the other side of the market, at least for a while. This is especially an issue in online platforms involving human experts as the expert resources are often scarce. The efficient utilization of experts in these p…

2017-03-02abs ↗pdf ↗

InvestLM: A Large Language Model for Investment using Financial Domain Instruction Tuningq-fin.GN

InvestLM is a financial domain LLM tuned on LLaMA-65B for investment advice.

problem Improving financial text understanding and advice generation for investment.

method Curated financial instruction dataset, LLaMA-65B, less-is-more-for-alignment approach.

result InvestLM provides comparable responses to state-of-the-art commercial models.

Investment advice Financial text understanding Large language model Instruction tuning Financial NLP benchmarks

2023-09-15abs ↗pdf ↗