Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates.
Continual Learning for Instruction Following from Realtime Feedback
Authors: Alane Suhr, Yoav Artzi
NeurIPS 2023 | Venue PDF | LLM Run Details | Input Tokens: 21,932 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 4,299 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We propose and deploy an approach to continually train an instruction-following agent from feedback provided by users during collaborative interactions. ... We evaluate through thousands of human-agent interactions, demonstrating 15.4% absolute improvement in instruction execution accuracy over time. |
| Researcher Affiliation | Academia | Alane Suhr University of California, Berkeley EMAIL Yoav Artzi Cornell University EMAIL |
| Pseudocode | Yes | Algorithm 1 Continual learning for instruction following from realtime user feedback. |
| Open Source Code | Yes | Our code and data is available here: https://github.com/lil-lab/clif_cb. |
| Open Datasets | Yes | Our code and data is available here: https://github.com/lil-lab/clif_cb. ... the demonstration training dataset D0 includes 8,790 instructions from 456 randomly-sampled human-human interactions from Suhr et al. [41]. |
| Dataset Splits | Yes | We use a held-out subset of the original CEREALBAR training set as a validation set for early stopping, comprising 5% of the original split. |
| Hardware Specification | Yes | We use a single Ge Force RTX 2080 Ti for training each model. |
| Software Dependencies | No | The paper mentions software components like 'BPE', 'LSTM RNN', 'LINGUNET', and 'ADAM' for optimization, but does not provide specific version numbers for these software dependencies. |
| Experiment Setup | Yes | For training, we use a batch size of 16 agent steps, a learning rate of 0.001, and ADAM [19] for optimization. |