Tootfinder

Without reading the article I can only think this is for the new #RobertRodriquez / #DannyTrejo movie:
`Dogchete`
"Its not about what do you did son, its about who you did it to. Machete was a man of focus, commitment, sheer will. I once saw him kill three vampires in a bar with a stapler.…

Haligonia.ca (@haligonia@mstdn.ca)
Attached: 1 image Police say machete and dog used in Prospect party altercation https://haligonia.ca/police-say-machete-and-dog-used-in-prospect-party-altercation-313449/?utm_source=dlvr.it&utm_medium=mastodon #halifax #novascotia #canada

On absurdia, että Helsinki poistaa suojateitä #Helsinki

On absurdia, että Helsinki poistaa suojateitä
Suojateiden poisto yritetään esittää jalankulkijoiden turvallisuutta edistävänä tekona.

HalluDetect: Detecting, Mitigating, and Benchmarking Hallucinations in Conversational Systems
Spandan Anaokar, Shrey Ganatra, Harshvivek Kashid, Swapnil Bhattacharyya, Shruti Nair, Reshma Sekhar, Siddharth Manohar, Rahul Hemrajani, Pushpak Bhattacharyya
https://arxiv.org/abs/2509.11619

HalluDetect: Detecting, Mitigating, and Benchmarking Hallucinations in Conversational Systems
Large Language Models (LLMs) are widely used in industry but remain prone to hallucinations, limiting their reliability in critical applications. This work addresses hallucination reduction in consumer grievance chatbots built using LLaMA 3.1 8B Instruct, a compact model frequently used in industry. We develop HalluDetect, an LLM-based hallucination detection system that achieves an F1 score of 69% outperforming baseline detectors by 25.44%. Benchmarking five chatbot architectures, we find that…

LLM Enhancement with Domain Expert Mental Model to Reduce LLM Hallucination with Causal Prompt Engineering
Boris Kovalerchuk, Brent D. Fegley
https://arxiv.org/abs/2509.10818 ht…

LLM Enhancement with Domain Expert Mental Model to Reduce LLM Hallucination with Causal Prompt Engineering
Difficult decision-making problems abound in various disciplines and domains. The proliferation of generative techniques, especially large language models (LLMs), has excited interest in using them for decision support. However, LLMs cannot yet resolve missingness in their training data, leading to hallucinations. Retrieval-Augmented Generation (RAG) enhances LLMs by incorporating external information retrieval, reducing hallucinations and improving accuracy. Yet, RAG and related methods are on…

Rewarding only 'interesting' answers worked out so well in Psychology, let's stick with it when training LLMs. https://theconversation.com/why-openais-…

In #Helsinki there's only one person I trust with repairing a #watch without screwing up (there was another previously, but he retired). Today I went and asked his name, let him know I've always been happy with his work and I'll go back with the next watch to repair the next time he has a shift there. …

The first step on the road to #TNC26 starts today… with the opening of the Call for Proposals!
Next year, our community will gather in Helsinki 🇫🇮 under the theme Digital Sisu—inspired by the Finnish word “sisu,” which embodies inner strength, tenacity, and determination in the face of adversity.
💡 If you have a story to share, or a vision that can shape the conversation—we want to hear f…

Unsupervised Hallucination Detection by Inspecting Reasoning Processes
Ponhvoan Srey, Xiaobao Wu, Anh Tuan Luu
https://arxiv.org/abs/2509.10004 https://arx…

Unsupervised Hallucination Detection by Inspecting Reasoning Processes
Unsupervised hallucination detection aims to identify hallucinated content generated by large language models (LLMs) without relying on labeled data. While unsupervised methods have gained popularity by eliminating labor-intensive human annotations, they frequently rely on proxy signals unrelated to factual correctness. This misalignment biases detection probes toward superficial or non-truth-related aspects, limiting generalizability across datasets and scenarios. To overcome these limitations…

Helsinki korottaa taas tonttivuokriaan, ja se voi olla helsinkiläisille hyvä tai huono uutinen #Helsinki

Helsinki korottaa taas tonttivuokriaan, ja se voi olla helsinkiläisille hyvä tai huono uutinen
Helsinki korottaa jälleen vuokria sadoilla asuintonteilla ja nyt myös siirtolapuutarhoissa. Se tuo kaupungille lisää tuloja ja monille helsinkiläisille lisää menoja.

Credal Transformer: A Principled Approach for Quantifying and Mitigating Hallucinations in Large Language Models
Shihao Ji, Zihui Song, Jiajie Huang
https://arxiv.org/abs/2510.12137

Credal Transformer: A Principled Approach for Quantifying and Mitigating Hallucinations in Large Language Models
Large Language Models (LLMs) hallucinate, generating factually incorrect yet confident assertions. We argue this stems from the Transformer's Softmax function, which creates "Artificial Certainty" by collapsing ambiguous attention scores into a single probability distribution, discarding uncertainty information at each layer. To fix this, we introduce the Credal Transformer, which replaces standard attention with a Credal Attention Mechanism (CAM) based on evidential theory. CAM produces a "cre…