Tootfinder

TIL that @… has sponsored articles. They don't try to hide it (it's at the top and bottom), but I didn't notice it at first. I got about a third of the way through when I realized it felt corpority.
It's not a bad article, but it's NOT news (as the site organizes it). I'll be glancing at the top more often now to make sure it's real now
https://www.bleepingcomputer.com/news/security/6-prompts-you-dont-want-employees-putting-in-microsoft-copilot/

KV-Runahead: Scalable Causal LLM Inference by Parallel Key-Value Cache Generation
Minsik Cho, Mohammad Rastegari, Devang Naik
https://arxiv.org/abs/2405.05329

KV-Runahead: Scalable Causal LLM Inference by Parallel Key-Value Cache Generation
Large Language Model or LLM inference has two phases, the prompt (or prefill) phase to output the first token and the extension (or decoding) phase to the generate subsequent tokens. In this work, we propose an efficient parallelization scheme, KV-Runahead to accelerate the prompt phase. The key observation is that the extension phase generates tokens faster than the prompt phase because of key-value cache (KV-cache). Hence, KV-Runahead parallelizes the prompt phase by orchestrating multiple pr…

This https://arxiv.org/abs/2303.17513 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Improving the Diproche CNL through Autoformalization via Large Language Models
The Diproche system is an automated proof checker for texts written in a controlled fragment of German, designed for didactical applications in classes introducing students to proofs for the first time. The first version of the system used a controlled natural language for which a Prolog formalization routine was written. In this paper, we explore the possibility of prompting large language models for autoformalization in the context of Diproche, with encouraging first results.

TIL that @… has sponsored articles. They don't try to hide it (it's at the top and bottom), but I didn't notice it at first. I got about a third of the way through when I realized it felt corpority.
It's not a bad article, but it's NOT news (as the site organizes it). I'll be glancing at the top more often now to make sure it's real now
https://www.bleepingcomputer.com/news/security/6-prompts-you-dont-want-employees-putting-in-microsoft-copilot/

Apprentices to Research Assistants: Advancing Research with Large Language Models
M. Namvarpour, A. Razi
https://arxiv.org/abs/2404.06404 https://

Apprentices to Research Assistants: Advancing Research with Large Language Models
Large Language Models (LLMs) have emerged as powerful tools in various research domains. This article examines their potential through a literature review and firsthand experimentation. While LLMs offer benefits like cost-effectiveness and efficiency, challenges such as prompt tuning, biases, and subjectivity must be addressed. The study presents insights from experiments utilizing LLMs for qualitative analysis, highlighting successes and limitations. Additionally, it discusses strategies for m…

This https://arxiv.org/abs/2312.14197 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models
The integration of large language models (LLMs) with external content has enabled more up-to-date and wide-ranging applications of LLMs, such as Microsoft Copilot. However, this integration has also exposed LLMs to the risk of indirect prompt injection attacks, where an attacker can embed malicious instructions within external content, compromising LLM output and causing responses to deviate from user expectations. To investigate this important but underexplored issue, we introduce the first be…

Logical Negation Augmenting and Debiasing for Prompt-based Methods
Yitian Li, Jidong Tian, Hao He, Yaohui Jin
https://arxiv.org/abs/2405.04872 https://

Logical Negation Augmenting and Debiasing for Prompt-based Methods
Prompt-based methods have gained increasing attention on NLP and shown validity on many downstream tasks. Many works have focused on mining these methods' potential for knowledge extraction, but few explore their ability to make logical reasoning. In this work, we focus on the effectiveness of the prompt-based methods on first-order logical reasoning and find that the bottleneck lies in logical negation. Based on our analysis, logical negation tends to result in spurious correlations to negativ…

Logical Negation Augmenting and Debiasing for Prompt-based Methods
Yitian Li, Jidong Tian, Hao He, Yaohui Jin
https://arxiv.org/abs/2405.04872 https://

Logical Negation Augmenting and Debiasing for Prompt-based Methods
Prompt-based methods have gained increasing attention on NLP and shown validity on many downstream tasks. Many works have focused on mining these methods' potential for knowledge extraction, but few explore their ability to make logical reasoning. In this work, we focus on the effectiveness of the prompt-based methods on first-order logical reasoning and find that the bottleneck lies in logical negation. Based on our analysis, logical negation tends to result in spurious correlations to negativ…

Will GPT-4 Run DOOM?
Adrian de Wynter
https://arxiv.org/abs/2403.05468 https://arxiv.org/pdf/2403.05468

Will GPT-4 Run DOOM?
We show that GPT-4's reasoning and planning capabilities extend to the 1993 first-person shooter Doom. This large language model (LLM) is able to run and play the game with only a few instructions, plus a textual description--generated by the model itself from screenshots--about the state of the game being observed. We find that GPT-4 can play the game to a passable degree: it is able to manipulate doors, combat enemies, and perform pathing. More complex prompting strategies involving multiple …

Will GPT-4 Run DOOM?
Adrian de Wynter
https://arxiv.org/abs/2403.05468 https://arxiv.org/pdf/2403.05468

Will GPT-4 Run DOOM?
We show that GPT-4's reasoning and planning capabilities extend to the 1993 first-person shooter Doom. This large language model (LLM) is able to run and play the game with only a few instructions, plus a textual description--generated by the model itself from screenshots--about the state of the game being observed. We find that GPT-4 can play the game to a passable degree: it is able to manipulate doors, combat enemies, and perform pathing. More complex prompting strategies involving multiple …