SLPL SHROOM at SemEval2024 Task 06: A comprehensive study on models ability to detect hallucination

2 code implementations • 7 Apr 2024 • Pouya Fallah, Soroush Gooran, Mohammad Jafarinasab, Pouya Sadeghi, Reza Farnia, Amirreza Tarabkhah, Zainab Sadat Taghavi, Hossein Sameti

Language models, particularly generative models, are susceptible to hallucinations, generating outputs that contradict factual knowledge or the source text.

Hallucination Machine Translation +3

Imaginations of WALL-E : Reconstructing Experiences with an Imagination-Inspired Module for Advanced AI Systems

no code implementations • 20 Aug 2023 • Zeinab Sadat Taghavi, Soroush Gooran, Seyed Arshan Dalili, Hamidreza Amirzadeh, Mohammad Jalal Nematbakhsh, Hossein Sameti

In this paper, we introduce a novel Artificial Intelligence (AI) system inspired by the philosophical and psychoanalytical concept of imagination as a ``Re-construction of Experiences".

Emotion Recognition Language Modelling +3

naab: A ready-to-use plug-and-play corpus for Farsi

1 code implementation • 29 Aug 2022 • Sadra Sabouri, Elnaz Rahmati, Soroush Gooran, Hossein Sameti

We propose naab, the biggest cleaned and ready-to-use open-source textual corpus in Farsi.