Nouha Dziri

Elastic Weight Removal for Faithful and Abstractive Dialogue Generation

2023 · arXiv (Cornell University)

Ideally, dialogue systems should generate responses that are faithful to the knowledge contained in relevant documents. However, many models generate hallucinated responses instead that contradict it or contain unverifiable information. To mitigate such undesirable behaviour, …

2 OLMo 2 Furious

2024 · arXiv (Cornell University)

We present OLMo 2, the next generation of our fully open language models. OLMo 2 includes a family of dense autoregressive language models at 7B, 13B and 32B scales with fully released artifacts -- model …

Automatic Dialogue Generation with Expressed Emotions

2018

Chenyang Huang, Osmar Zaïane, Amine Trabelsi, Nouha Dziri. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers). 2018.

Self-Refine: Iterative Refinement with Self-Feedback

2023 · arXiv (Cornell University)

Like humans, large language models (LLMs) do not always generate the best output on their first try. Motivated by how humans refine their written text, we introduce Self-Refine, an approach for improving initial outputs from …