Research
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

1122 · Aug 201819922001200920172026
32 results for chatbot

Meena is a chatbot trained on social media data, achieving human-like conversation quality.

problem Creating a chatbot that can have human-like conversations in an open-domain setting.
method End-to-end training of a 2.6B parameter neural network on social media data, using perplexity and a human evaluation metric (SSA) to assess quality.
result Meena achieves a high human-like conversation quality (79% SSA) when compared to existing chatbots.

Chatbot uses BERT to handle financial investment questions, improving accuracy and decision-making.

problem Improving accuracy and decision-making in financial investment customer service.
method Deep Bidirectional Transformer (BERT) model, uncertainty measure comparison, mixed-integer programming, automatic spelling correction.
result Chatbot can recognize 381 intents and decide when to escalate questions.

The majority of conversations a dialogue agent sees over its lifetime occur after it has already been trained and deployed, leaving a vast store of potential training signal untapped. In this work, we propose the self-feeding chatbot, a dialogue agent with the ability to extract new training examples from the conversat…

2019-01-16abs ↗pdf ↗

In this paper, we present a real-world conversational AI system to search for and book hotels through text messaging. Our architecture consists of a frame-based dialogue management system, which calls machine learning models for intent classification, named entity recognition, and information retrieval subtasks. Our ch…

2019-08-27abs ↗pdf ↗

We study reinforcement learning of chatbots with recurrent neural network architectures when the rewards are noisy and expensive to obtain. For instance, a chatbot used in automated customer service support can be scored by quality assurance agents, but this process can be expensive, time consuming and noisy. Previous …

2017-02-10abs ↗pdf ↗

Dropping a tiny fraction of preferences can significantly alter the rankings of top LLMs.

problem Robustness of LLM ranking systems to small changes in preference data.
method A computational method based on the Bradley-Terry model to evaluate robustness.
result Top LLM rankings can be highly sensitive to the removal of a small fraction of preferences.

Study uses chatbot to understand users' needs for ML model explanations.

problem Lack of understanding of user needs for model explanations.
method Developed a conversational system (dr_ant) to collect user questions about a machine learning model trained on Titanic data.
result Collected a corpus of 1000+ dialogues to identify common user questions.

We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon Alexa Prize competition. MILABOT is capable of conversing with humans on popular small talk topics through both speech and text. The system consists of an ensemble of natural langu…

2018-01-20abs ↗pdf ↗

We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon Alexa Prize competition. MILABOT is capable of conversing with humans on popular small talk topics through both speech and text. The system consists of an ensemble of natural langu…

2017-09-07abs ↗pdf ↗

Quriosity analyzes curiosity-driven questions from diverse sources.

problem Understanding and analyzing human curiosity-driven questions.
method Collection of 13.5K questions from various sources, development of an iterative prompt improvement framework.
result 42% of questions are causal, revealing unique linguistic properties.

Low-rank framework for task-specific LLM ranking from sparse comparisons.

problem Challenges in reliable task-specific ranking of LLMs under sparse, imbalanced comparisons.
method Low-rank modeling of task-by-model ability matrix, max-norm accurate estimator, task-wise top-K recovery guarantees, uncertainty quantification framework.
result Improves sample efficiency and produces tighter, better-calibrated ranking certificates.

AI helps simplify complex ship finance processes.

problem Complexity in ship finance due to data and regulatory requirements.
method Integrates large language models for document comprehension, information extraction, and workflow automation.
result AI-assisted systems can support maritime finance professionals in managing complex information and reporting requirements.

CJE calibrates cheap LLM judges against an oracle, achieving high accuracy at a fraction of the cost.

problem Inexpensive LLM judges can produce biased rankings, leading to unreliable outcomes.
method CJE uses a small oracle to calibrate cheap scores, then evaluates at scale with valid uncertainty.
result CJE achieves 99% pairwise ranking accuracy at 14x lower cost compared to a 16x oracle/judge cost ratio.

Improved NER performance on imbalanced data.

problem Highly unbalanced training data in NER tasks.
method Adapted a neural architecture with CRF and BI-LSTM layers, using pre-trained embeddings. Introduced a two-class split to optimize performance.
result Significant improvement in performance for weak classes with minimal training data.

Proposes an iterative algorithm for optimizing attention mechanisms in large language models.

problem Optimizing attention mechanisms in large language models.
method Iterative algorithm for rescaled hyperbolic functions regression.
result Efficiency and generalizability of the rescaled softmax regression framework.

We provide an online RLHF workflow for large language models.

problem Lack of online RLHF workflow for large language models.
method Construct preference models using open-source datasets, approximate human feedback, and implement online iterative RLHF.
result Our LLM achieves state-of-the-art performance on various benchmarks.

Algorithm reduces audit costs by identifying best service configurations from biased textual evidence.

problem Designing service systems from textual evidence requires accurate selection despite biased automated scoring.
method Developed PP-LUCB algorithm combining LLM scores and selective audits to minimize costs.
result Correctly identified the best model in 40/40 trials with 90% cost reduction.

New method accounts for hidden context in preference learning for RLHF models.

problem Incomplete data with hidden context affects RLHF model outcomes.
method Distributional Preference Learning (DPL) methods estimate hidden context distributions.
result DPL methods reduce RLHF vulnerabilities by accounting for hidden context.

Develops a statistical framework to measure uncertainty in model rankings based on human preferences.

problem Uncertainty in model rankings based on human preferences due to mismatch between human and model preferences.
method Statistical framework using pairwise comparisons by humans and models to provide rank-sets for each model.
result Rank-sets constructed using only pairwise comparisons by strong models often do not cover the true ranking of human preferences.

Study human-machine interaction with private info using offline RL.

problem Confounding bias and distributional mismatch in offline RL for human-guided interaction.
method Developed a novel identification result and OPE method to address confounding bias, and used pessimism to tackle distributional mismatch.
result Policy pair converges to optimal one at satisfactory rate under mild assumptions.

Proposes a new algorithm for efficient online model selection of LLMs considering the increasing-then-converging trend.

problem Balancing cost and performance in choosing the best LLM among a diverse set of models.
method Introduces a time-increasing bandit algorithm (TI-UCB) that predicts model performance increases and balances exploration and exploitation.
result Achieves a logarithmic regret upper bound, indicating a fast convergence rate in model selection.