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.

168,982 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “persona-based”

A Persona-based Multi-turn Conversation Model in an Adversarial Learning Frameworkcs.CL

Enhances persona-based conversation model for multi-turn dialogue.

problem Improving persona-based conversation models for multi-turn dialogue.

method Introduced additional input modality into hredGAN to capture external attributes.

result Persona hredGAN (

phredGAN

) outperforms existing models in multi-turn dialogue corpora.

persona-based conversation multi-turn dialogue hredGAN external attributes perplexity

2019-04-29abs ↗pdf ↗

An Adversarial Learning Framework For A Persona-Based Multi-Turn Dialogue Modelcs.CL

Enhances dialogue model with persona attributes using adversarial learning.

problem Improving dialogue models to better capture speaker identity and topic.

method Adversarial learning framework with a dual discriminator system.

result phredGAN outperforms persona Seq2Seq model in various datasets.

dialogue models persona-based adversarial learning multi-turn speaker attributes

2019-04-29abs ↗pdf ↗

Adaptive Querying with AI Persona Priorsstat.ML

Adaptive querying learns user psychometrics with AI personas.

problem Learning user psychometrics within query budgets.

method Persona-induced latent variable model with AI personas and large language model response distributions.

result Persona-based posteriors deliver accurate probabilistic predictions.

adaptive querying psychometrics AI personas large language model Bayesian design

2026-05-01abs ↗pdf ↗

A relevance-scalability-interpretability tradeoff with temporally evolving user personasstat.ML

The current work characterizes the users of a VoD streaming space through user-personas based on a tenure timeline and temporal behavioral features in the absence of explicit user profiles. A combination of tenure timeline and temporal characteristics caters to business needs of understanding the evolution and phases o…

2017-04-25abs ↗pdf ↗

Efficient Clustering with Provable Guardrails for LLM Inference at Scalecs.LG

New algorithm clusters LLM inputs efficiently with quality control.

problem Scaling LLM inference cost and latency for millions of users.

method Two-stage algorithm using Mini-batch K-Means and greedy selection of representatives.

result Enforces similarity and attribute guardrails exactly, scales to tens of millions of samples.

LLM inference clustering quality control set cover embedding space

2026-07-22abs ↗pdf ↗