Tootfinder

Na, super. Ich hatte neulich mal jemandem, der „der Junge“ in der Klausur als Dativ eingeordnet hatte, geraten, doch noch mal drüber nachzudenken, ob er/sie wirklich im Master Linguistik studieren will. Vielleicht doch noch mal Grundkurs im BA, denn eigentlich ist das ja dritte Klasse in der Schule.
Nun hat @… einen Fehler in der Grammatiktheorie gefunden. Da steht „des“ für einen Artikel im Nominativ. Und zwar seit 2010. In der deutschen Ausgabe. Dann Übersetzung. Proofreading. Hunderte Lehrveranstaltungen. Es hat nie jemand gesehen.
Also: Glaubt niemandem! Schon gar nicht Euch selber. Und wenn Ihr was nicht versteht, dann so lange nachfragen bzw. nachdenken, bis Ihr es versteht.
Viel Spaß!
PS: In den Folien kommt diese Passage nicht vor. Sonst hätte ich es wohl gemerkt. Das Buch selbst gucke ich nur selten an.

CFaiRLLM: Consumer Fairness Evaluation in Large-Language Model Recommender System
Yashar Deldjoo, Tommaso di Noia
https://arxiv.org/abs/2403.05668 https://…

CFaiRLLM: Consumer Fairness Evaluation in Large-Language Model Recommender System
In the evolving landscape of recommender systems, the integration of Large Language Models (LLMs) such as ChatGPT marks a new era, introducing the concept of Recommendation via LLM (RecLLM). While these advancements promise unprecedented personalization and efficiency, they also bring to the fore critical concerns regarding fairness, particularly in how recommendations might inadvertently perpetuate or amplify biases associated with sensitive user attributes. In order to address these concerns,…

Na, super. Ich hatte neulich mal jemandem, der „der Junge“ in der Klausur als Dativ eingeordnet hatte, geraten, doch noch mal drüber nachzudenken, ob er/sie wirklich im Master Linguistik studieren will. Vielleicht doch noch mal Grundkurs im BA, denn eigentlich ist das ja dritte Klasse in der Schule.
Nun hat @… einen Fehler in der Grammatiktheorie gefunden. Da steht „des“ für einen Artikel im Nominativ. Und zwar seit 2010. In der deutschen Ausgabe. Dann Übersetzung. Proofreading. Hunderte Lehrveranstaltungen. Es hat nie jemand gesehen.
Also: Glaubt niemandem! Schon gar nicht Euch selber. Und wenn Ihr was nicht versteht, dann so lange nachfragen bzw. nachdenken, bis Ihr es versteht.
Viel Spaß!
PS: In den Folien kommt diese Passage nicht vor. Sonst hätte ich es wohl gemerkt. Das Buch selbst gucke ich nur selten an.

This https://arxiv.org/abs/2310.09499 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

One-Shot Sensitivity-Aware Mixed Sparsity Pruning for Large Language Models
Various Large Language Models(LLMs) from the Generative Pretrained Transformer(GPT) family have achieved outstanding performances in a wide range of text generation tasks. However, the enormous model sizes have hindered their practical use in real-world applications due to high inference latency. Therefore, improving the efficiencies of LLMs through quantization, pruning, and other means has been a key issue in LLM studies. In this work, we propose a method based on Hessian sensitivity-aware mi…

MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
Shengding Hu, Yuge Tu, Xu Han, Chaoqun He, Ganqu Cui, Xiang Long, Zhi Zheng, Yewei Fang, Yuxiang Huang, Weilin Zhao, Xinrong Zhang, Zheng Leng Thai, Kaihuo Zhang, Chongyi Wang, Yuan Yao, Chenyang Zhao, Jie Zhou, Jie Cai, Zhongwu Zhai, Ning Ding, Chao Jia, Guoyang Zeng, Dahai Li, Zhiyuan Liu, Maosong Sun

MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
The burgeoning interest in developing Large Language Models (LLMs) with up to trillion parameters has been met with concerns regarding resource efficiency and practical expense, particularly given the immense cost of experimentation. This scenario underscores the importance of exploring the potential of Small Language Models (SLMs) as a resource-efficient alternative. In this context, we introduce MiniCPM, specifically the 1.2B and 2.4B non-embedding parameter variants, not only excel in their …

SPA: Towards A Computational Friendly Cloud-Base and On-Devices Collaboration Seq2seq Personalized Generation
Yanming Liu, Xinyue Peng, Jiannan Cao, Le Dai, Xingzu Liu, Weihao Liu, Mingbang Wang
https://arxiv.org/abs/2403.07088

SPA: Towards A Computational Friendly Cloud-Base and On-Devices Collaboration Seq2seq Personalized Generation
Large language models(LLMs) have shown its outperforming ability on various tasks and question answering. However, LLMs require high computation cost and large memory cost. At the same time, LLMs may cause privacy leakage when training or prediction procedure contains sensitive information. In this paper, we propose SPA(Side Plugin Adaption), a lightweight architecture for fast on-devices inference and privacy retaining on the constraints of strict on-devices computation and memory constraints.…

SPA: Towards A Computational Friendly Cloud-Base and On-Devices Collaboration Seq2seq Personalized Generation
Yanming Liu, Xinyue Peng, Jiannan Cao, Le Dai, Xingzu Liu, Weihao Liu, Mingbang Wang
https://arxiv.org/abs/2403.07088

SPA: Towards A Computational Friendly Cloud-Base and On-Devices Collaboration Seq2seq Personalized Generation
Large language models(LLMs) have shown its outperforming ability on various tasks and question answering. However, LLMs require high computation cost and large memory cost. At the same time, LLMs may cause privacy leakage when training or prediction procedure contains sensitive information. In this paper, we propose SPA(Side Plugin Adaption), a lightweight architecture for fast on-devices inference and privacy retaining on the constraints of strict on-devices computation and memory constraints.…

Improving Reinforcement Learning from Human Feedback Using Contrastive Rewards
Wei Shen, Xiaoying Zhang, Yuanshun Yao, Rui Zheng, Hongyi Guo, Yang Liu
https://arxiv.org/abs/2403.07708

Improving Reinforcement Learning from Human Feedback Using Contrastive Rewards
Reinforcement learning from human feedback (RLHF) is the mainstream paradigm used to align large language models (LLMs) with human preferences. Yet existing RLHF heavily relies on accurate and informative reward models, which are vulnerable and sensitive to noise from various sources, e.g. human labeling errors, making the pipeline fragile. In this work, we improve the effectiveness of the reward model by introducing a penalty term on the reward, named as \textit{contrastive rewards}. %Contrast…

Improving Reinforcement Learning from Human Feedback Using Contrastive Rewards
Wei Shen, Xiaoying Zhang, Yuanshun Yao, Rui Zheng, Hongyi Guo, Yang Liu
https://arxiv.org/abs/2403.07708

Improving Reinforcement Learning from Human Feedback Using Contrastive Rewards
Reinforcement learning from human feedback (RLHF) is the mainstream paradigm used to align large language models (LLMs) with human preferences. Yet existing RLHF heavily relies on accurate and informative reward models, which are vulnerable and sensitive to noise from various sources, e.g. human labeling errors, making the pipeline fragile. In this work, we improve the effectiveness of the reward model by introducing a penalty term on the reward, named as \textit{contrastive rewards}. %Contrast…

This https://arxiv.org/abs/2309.08173 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

FedJudge: Federated Legal Large Language Model
Large Language Models (LLMs) have gained prominence in the field of Legal Intelligence, offering potential applications in assisting legal professionals and laymen. However, the centralized training of these Legal LLMs raises data privacy concerns, as legal data is distributed among various institutions containing sensitive individual information. This paper addresses this challenge by exploring the integration of Legal LLMs with Federated Learning (FL) methodologies. By employing FL, Legal LLM…