Papers by Mojtaba Komeili
Chain-of-Verification Reduces Hallucination in Large Language Models (2024.findings-acl)
Copied to clipboard
Shehzaad Dhuliawala, Mojtaba Komeili, Jing Xu, Roberta Raileanu, Xian Li, Asli Celikyilmaz, Jason Weston
| Challenge: | Large language models can generate plausible but incorrect factual information, termed hallucinations, but they can still fail on lesser known facts. |
| Approach: | They develop a method that allows language models to deliberate on the responses they give in order to correct their errors. |
| Outcome: | The proposed method decreases hallucinations across a variety of tasks, including list-based questions, closed book MultiSpanQA and longform text generation. |
Internet-Augmented Dialogue Generation (2022.acl-long)
Copied to clipboard
| Challenge: | Large language models are known to hallucinate facts when generating dialogue, and are unable to encode the knowledge in the model at the point of training. |
| Approach: | They propose an approach that generates an internet search query based on the context and conditions on the results to generate a response. |
| Outcome: | The proposed model generates an internet search query and then conditions on the results to generate a response. |
Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Language models (LMs) have been shown to generate more factual responses by employing modularity in combination with retrieval. |
| Approach: | They extend the recent approach of Adolphs et al. (2021) to include internet search as a module. |
| Outcome: | The proposed method outperforms the state-of-the-art model BlenderBot 2 on open-domain knowledge-grounded conversations for the same number of parameters. |
Learning New Skills after Deployment: Improving open-domain internet-driven dialogue with human feedback (2023.acl-long)
Copied to clipboard
| Challenge: | Frozen models trained to mimic static datasets can never improve their performance. |
| Approach: | They propose to use binary quality measurements and free-form text feedback to improve conversational skills in a conversational learning framework. |
| Outcome: | The proposed model improves on the DIRECTOR model, which is based on binary quality measurements and free-form text feedback, and shows that iterative retraining and redeployment can improve the model. |