MétaCan
Menu
Back to cohort

Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-Talk

2024· article· en· W4402670735 on OpenAlexaff
Dennis Ulmer, Elman Mansimov, Kaixiang Lin, Lijia Sun, Xibin Gao, Yi Zhang

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicSpeech and dialogue systems
Canadian institutionsArtificial Intelligence in Medicine (Canada)
Fundersnot available
KeywordsComputer scienceBootstrapping (finance)Task (project management)Human–computer interactionEngineeringSystems engineeringBusiness

Abstract

fetched live from OpenAlex

Large language models (LLMs) are powerful dialogue agents, but specializing them towards fulfilling a specific function can be challenging.Instructing tuning, i.e. tuning models on instruction and sample responses generated by humans (Ouyang et al., 2022), has proven as an effective method to do so, yet requires a number of data samples that a) might not be available or b) costly to generate.Furthermore, this cost increases when the goal is to make the LLM follow a specific workflow within a dialogue instead of single instructions.Inspired by the self-play technique in reinforcement learning and the use of LLMs to simulate human agents, we propose a more effective method for data collection through LLMs engaging in a conversation in various roles.This approach generates a training data via "self-talk" of LLMs that can be refined and utilized for supervised fine-tuning.We introduce an automated way to measure the (partial) success of a dialogue.This metric is used to filter the generated conversational data that is fed back in LLM for training.Based on our automated and human evaluations of conversation quality, we demonstrate that such self-talk data improves results.In addition, we examine the various characteristics that showcase the quality of generated dialogues and how they can be connected to their potential utility as training data.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesInsufficient payload (model declined to judge)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.985
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.015
GPT teacher head0.242
Teacher spread0.227 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations9
Published2024
Admission routes1
Has abstractyes

Explore more

Same topicSpeech and dialogue systemsFrench-language works237,207