1 code implementation • 16 Apr 2024 • Huihan Li, Liwei Jiang, Jena D. Huang, Hyunwoo Kim, Sebastin Santy, Taylor Sorensen, Bill Yuchen Lin, Nouha Dziri, Xiang Ren, Yejin Choi
As the utilization of large language models (LLMs) has proliferated worldwide, it is crucial for them to have adequate knowledge and fair representation for diverse global cultures.
1 code implementation • 20 Mar 2024 • Nathan Lambert, Valentina Pyatkin, Jacob Morrison, LJ Miranda, Bill Yuchen Lin, Khyathi Chandu, Nouha Dziri, Sachin Kumar, Tom Zick, Yejin Choi, Noah A. Smith, Hannaneh Hajishirzi
In this paper, we present RewardBench, a benchmark dataset and code-base for evaluation, to enhance scientific understanding of reward models.
1 code implementation • 7 Feb 2024 • Taylor Sorensen, Jared Moore, Jillian Fisher, Mitchell Gordon, Niloofar Mireshghallah, Christopher Michael Rytting, Andre Ye, Liwei Jiang, Ximing Lu, Nouha Dziri, Tim Althoff, Yejin Choi
We identify and formalize three possible ways to define and operationalize pluralism in AI systems: 1) Overton pluralistic models that present a spectrum of reasonable responses; 2) Steerably pluralistic models that can steer to reflect certain perspectives; and 3) Distributionally pluralistic models that are well-calibrated to a given population in distribution.
no code implementations • 4 Dec 2023 • Bill Yuchen Lin, Abhilasha Ravichander, Ximing Lu, Nouha Dziri, Melanie Sclar, Khyathi Chandu, Chandra Bhagavatula, Yejin Choi
We analyze the effect of alignment tuning by examining the token distribution shift between base LLMs and their aligned counterpart.
no code implementations • 31 Oct 2023 • Peter West, Ximing Lu, Nouha Dziri, Faeze Brahman, Linjie Li, Jena D. Hwang, Liwei Jiang, Jillian Fisher, Abhilasha Ravichander, Khyathi Chandu, Benjamin Newman, Pang Wei Koh, Allyson Ettinger, Yejin Choi
Specifically, we propose and test the Generative AI Paradox hypothesis: generative models, having been trained directly to reproduce expert-like outputs, acquire generative capabilities that are not contingent upon -- and can therefore exceed -- their ability to understand those same types of outputs.
no code implementations • 24 Oct 2023 • Kavel Rao, Liwei Jiang, Valentina Pyatkin, Yuling Gu, Niket Tandon, Nouha Dziri, Faeze Brahman, Yejin Choi
From this model we distill a high-quality dataset, \delta-Rules-of-Thumb, of 1. 2M entries of contextualizations and rationales for 115K defeasible moral actions rated highly by human annotators 85. 9% to 99. 8% of the time.
1 code implementation • 12 Oct 2023 • Linlu Qiu, Liwei Jiang, Ximing Lu, Melanie Sclar, Valentina Pyatkin, Chandra Bhagavatula, Bailin Wang, Yoon Kim, Yejin Choi, Nouha Dziri, Xiang Ren
The ability to derive underlying principles from a handful of observations and then generalize to novel situations -- known as inductive reasoning -- is central to human intelligence.
1 code implementation • 2 Sep 2023 • Taylor Sorensen, Liwei Jiang, Jena Hwang, Sydney Levine, Valentina Pyatkin, Peter West, Nouha Dziri, Ximing Lu, Kavel Rao, Chandra Bhagavatula, Maarten Sap, John Tasioulas, Yejin Choi
To improve AI systems to better reflect value pluralism, the first-order challenge is to explore the extent to which AI systems can model pluralistic human values, rights, and duties as well as their interaction.
no code implementations • NeurIPS 2023 • Zeqiu Wu, Yushi Hu, Weijia Shi, Nouha Dziri, Alane Suhr, Prithviraj Ammanabrolu, Noah A. Smith, Mari Ostendorf, Hannaneh Hajishirzi
We introduce Fine-Grained RLHF, a framework that enables training and learning from reward functions that are fine-grained in two respects: (1) density, providing a reward after every segment (e. g., a sentence) is generated; and (2) incorporating multiple reward models associated with different feedback types (e. g., factual incorrectness, irrelevance, and information incompleteness).
1 code implementation • NeurIPS 2023 • Nouha Dziri, Ximing Lu, Melanie Sclar, Xiang Lorraine Li, Liwei Jiang, Bill Yuchen Lin, Peter West, Chandra Bhagavatula, Ronan Le Bras, Jena D. Hwang, Soumya Sanyal, Sean Welleck, Xiang Ren, Allyson Ettinger, Zaid Harchaoui, Yejin Choi
We formulate compositional tasks as computation graphs to systematically quantify the level of complexity, and break down reasoning steps into intermediate sub-procedures.
1 code implementation • 24 May 2023 • Ximing Lu, Faeze Brahman, Peter West, Jaehun Jang, Khyathi Chandu, Abhilasha Ravichander, Lianhui Qin, Prithviraj Ammanabrolu, Liwei Jiang, Sahana Ramnath, Nouha Dziri, Jillian Fisher, Bill Yuchen Lin, Skyler Hallinan, Xiang Ren, Sean Welleck, Yejin Choi
While extreme-scale language models have demonstrated exceptional performance on a variety of language tasks, the degree of control over these language models through pure prompting can often be limited.
1 code implementation • 11 May 2023 • Ehsan Kamalloo, Nouha Dziri, Charles L. A. Clarke, Davood Rafiei
The recent success of large language models (LLMs) for QA aggravates lexical matching failures since candidate answers become longer, thereby making matching with the gold answers even more challenging.
2 code implementations • NeurIPS 2023 • Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, Shashank Gupta, Bodhisattwa Prasad Majumder, Katherine Hermann, Sean Welleck, Amir Yazdanbakhsh, Peter Clark
Motivated by how humans refine their written text, we introduce Self-Refine, an approach for improving initial outputs from LLMs through iterative feedback and refinement.
1 code implementation • 30 Mar 2023 • Nico Daheim, Nouha Dziri, Mrinmaya Sachan, Iryna Gurevych, Edoardo M. Ponti
We evaluate our method -- using different variants of Flan-T5 as a backbone language model -- on multiple datasets for information-seeking dialogue generation and compare our method with state-of-the-art techniques for faithfulness, such as CTRL, Quark, DExperts, and Noisy Channel reranking.
1 code implementation • ICCV 2023 • Seungju Han, Jack Hessel, Nouha Dziri, Yejin Choi, Youngjae Yu
To train CHAMPAGNE, we collect and release YTD-18M, a large-scale corpus of 18M video-based dialogues.
1 code implementation • 22 Apr 2022 • Nouha Dziri, Ehsan Kamalloo, Sivan Milton, Osmar Zaiane, Mo Yu, Edoardo M. Ponti, Siva Reddy
The goal of information-seeking dialogue is to respond to seeker queries with natural language utterances that are grounded on knowledge sources.
1 code implementation • NAACL 2022 • Nouha Dziri, Sivan Milton, Mo Yu, Osmar Zaiane, Siva Reddy
Knowledge-grounded conversational models are known to suffer from producing factually invalid statements, a phenomenon commonly called hallucination.
no code implementations • 25 Jun 2021 • Alessandro Sordoni, Nouha Dziri, Hannes Schulz, Geoff Gordon, Phil Bachman, Remi Tachet
We propose decomposing the full MI estimation problem into a sum of smaller estimation problems by splitting one of the views into progressively more informed subviews and by applying the chain rule on MI between the decomposed views.
1 code implementation • 30 Apr 2021 • Nouha Dziri, Hannah Rashkin, Tal Linzen, David Reitter
To this end, we introduce the Benchmark for Evaluation of Grounded INteraction (BEGIN), comprised of 12k dialogue turns generated by neural dialogue systems trained on three knowledge-grounded dialogue corpora.
1 code implementation • EMNLP 2021 • Nouha Dziri, Andrea Madotto, Osmar Zaiane, Avishek Joey Bose
Dialogue systems powered by large pre-trained language models (LM) exhibit an innate ability to deliver fluent and natural-looking responses.
no code implementations • 1 Jan 2021 • Alessandro Sordoni, Nouha Dziri, Hannes Schulz, Geoff Gordon, Remi Tachet des Combes, Philip Bachman
In this paper, we transform each view into a set of subviews and then decompose the original MI bound into a sum of bounds involving conditional MI between the subviews.
1 code implementation • NAACL 2019 • Nouha Dziri, Ehsan Kamalloo, Kory W. Mathewson, Osmar Zaiane
Evaluating open-domain dialogue systems is difficult due to the diversity of possible correct answers.
1 code implementation • WS 2019 • Nouha Dziri, Ehsan Kamalloo, Kory W. Mathewson, Osmar Zaiane
Our model is built upon the basic Seq2Seq model by augmenting it with a hierarchical joint attention mechanism that incorporates topical concepts and previous interactions into the response generation.
1 code implementation • NAACL 2018 • Chenyang Huang, Osmar Za{\"\i}ane, Amine Trabelsi, Nouha Dziri
Despite myriad efforts in the literature designing neural dialogue generation systems in recent years, very few consider putting restrictions on the response itself.