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 “Self-Reflection”

Finding the Sweet Spot: Trading Quality, Cost, and Speed During Inference-Time LLM Reflectionstat.ML

This paper compares self-reflection and budget tuning for LLMs, revealing domain-specific performance gains.

problem Improving inference-time performance of LLMs without retraining, balancing quality, cost, and latency.

method Systematic comparison of self-reflection and budget tuning across mathematical reasoning and translation tasks, evaluating various LLMs and model families.

result Substantial domain-dependent variation in self-reflection effectiveness, with up to 220% performance gains in mathematical reasoning.

Large Language Models Inference Time Self-Reflection Budget Tuning Mathematical Reasoning

2025-10-23abs ↗pdf ↗

Self-Reflective Variational Autoencodercs.LG

Self-reflective VAE improves inference and generative modeling without complex components.

problem Limitations of typical VAEs in inference and generative modeling.

method Introduces self-reflective inference, a new hierarchical structure that matches variational posterior to exact posterior.

result Self-reflective inference achieves state-of-the-art performance on binarized MNIST without autoregressive layers.

VAE Variational Inference Generative Modeling Neural Autoregressive Models Self-Reflective Inference

2020-07-10abs ↗pdf ↗

Learning to Generate Explainable Stock Predictions using Self-Reflective Large Language Modelscs.LG

SEP framework teaches LLMs to generate explainable stock predictions.

problem Challenging task of generating human-readable explanations for stock predictions.

method Self-reflective agent and Proximal Policy Optimization (PPO) for autonomous learning.

result Fine-tuned LLM outperforms traditional methods in prediction accuracy and Matthews correlation coefficient.

stock prediction explainable AI large language models self-reflective agent Proximal Policy Optimization

2024-02-06abs ↗pdf ↗

Language Models and Cycle Consistency for Self-Reflective Machine Translationcs.CL

This paper uses LLMs and cycle consistency for better machine translation evaluation.

problem Evaluating translation quality and LLM capabilities without ground truth.

method Generate translation candidates, back-translate, and evaluate cycle consistency.

result Larger LLMs or more inference passes improve cycle consistency.

machine translation language models cycle consistency evaluation translation quality

2024-11-05abs ↗pdf ↗

Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoningcs.LG

Bayesian RL enhances LLMs to reflectively explore and correct errors.

problem LLMs trained via RL lack reflective behaviors like rethinking and error correction.

method Bayesian RL framework that optimizes expected return under posterior distribution over Markov decision processes.

result BARL algorithm improves LLM performance in reasoning tasks.

Bayesian RL Reflective Exploration LLM Reasoning Reinforcement Learning Markov Decision Processes

2025-05-26abs ↗pdf ↗