Zobrazeno 1 - 10
of 30
pro vyhledávání: '"Dhuliawala, Shehzaad"'
Autor:
Dhuliawala, Shehzaad, Kulikov, Ilia, Yu, Ping, Celikyilmaz, Asli, Weston, Jason, Sukhbaatar, Sainbayar, Lanchantin, Jack
During language model decoding, it is known that using higher temperature sampling gives more creative responses, while lower temperatures are more factually accurate. However, such models are commonly applied to general instruction following, which
Externí odkaz:
http://arxiv.org/abs/2411.09661
We present ALT (ALignment with Textual feedback), an approach that aligns language models with user preferences expressed in text. We argue that text offers greater expressiveness, enabling users to provide richer feedback than simple comparative pre
Externí odkaz:
http://arxiv.org/abs/2407.16970
Autor:
Jin, Zhijing, Heil, Nils, Liu, Jiarui, Dhuliawala, Shehzaad, Qi, Yahang, Schölkopf, Bernhard, Mihalcea, Rada, Sachan, Mrinmaya
Implicit Personalization (IP) is a phenomenon of language models inferring a user's background from the implicit cues in the input prompts and tailoring the response based on this inference. While previous work has touched upon various instances of t
Externí odkaz:
http://arxiv.org/abs/2405.14808
In a human-AI collaboration, users build a mental model of the AI system based on its reliability and how it presents its decision, e.g. its presentation of system confidence and an explanation of the output. Modern NLP systems are often uncalibrated
Externí odkaz:
http://arxiv.org/abs/2310.13544
Autor:
Dhuliawala, Shehzaad, Komeili, Mojtaba, Xu, Jing, Raileanu, Roberta, Li, Xian, Celikyilmaz, Asli, Weston, Jason
Generation of plausible yet incorrect factual information, termed hallucination, is an unsolved issue in large language models. We study the ability of language models to deliberate on the responses they give in order to correct their mistakes. We de
Externí odkaz:
http://arxiv.org/abs/2309.11495
We present a latent variable model for classification that provides a novel probabilistic interpretation of neural network softmax classifiers. We derive a variational objective to train the model, analogous to the evidence lower bound (ELBO) used to
Externí odkaz:
http://arxiv.org/abs/2305.10406
Decision-makers in the humanitarian sector rely on timely and exact information during crisis events. Knowing how many civilians were injured during an earthquake is vital to allocate aids properly. Information about such victim counts is often only
Externí odkaz:
http://arxiv.org/abs/2302.12367
Autor:
Zouhar, Vilém, Dhuliawala, Shehzaad, Zhou, Wangchunshu, Daheim, Nico, Kocmi, Tom, Jiang, Yuchen Eleanor, Sachan, Mrinmaya
Machine translation quality estimation (QE) predicts human judgements of a translation hypothesis without seeing the reference. State-of-the-art QE systems based on pretrained language models have been achieving remarkable correlations with human jud
Externí odkaz:
http://arxiv.org/abs/2301.09008
In typical machine learning systems, an estimate of the probability of the prediction is used to assess the system's confidence in the prediction. This confidence measure is usually uncalibrated; i.e.\ the system's confidence in the prediction does n
Externí odkaz:
http://arxiv.org/abs/2203.10623
Text-based games (TBG) have emerged as promising environments for driving research in grounded language understanding and studying problems like generalization and sample efficiency. Several deep reinforcement learning (RL) methods with varying archi
Externí odkaz:
http://arxiv.org/abs/2110.08470