Influence Function Based Second-Order Channel Pruning-Evaluating True Loss Changes For Pruning Is Possible Without Retraining

Large Language Models (LLMs) usually suffer from knowledge cutoff or fallacy issues, which means they are unaware of unseen events or generate text with incorrect facts owing to the outdated/noisy data.

This paper describes the systems submitted by team6 for ChatEval, the DSTC 11 Track 4 competition.

Objective and subjective evaluations show that \textit{Phoneme Hallucinator} outperforms existing VC methods for both intelligibility and speaker similarity.

We propose a training-assisted bit flip attack, in which the adversary is involved in the training stage to build a high-risk model to release.

In this paper, we propose a novel task, Proactive News Grounded Conversation, in which a dialogue system can proactively lead the conversation based on some key topics of the news.

Hyper-relational knowledge graph completion (HKGC) aims at inferring unknown triples while considering its qualifiers.