WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia · HackerPapers discussions

WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia — mentioned by emrek1

Tue, 12 Mar 2024 01:20:05 GMT

Each of those is great, and more sophisticated strategies are being developed all the time: incorporating static analysis at inference time to ensure code is more than just syntactically correct [0]; to multi-LLM call agent-based frameworks [1]; decomposing hard tasks into many "easier" LLM tasks [2]; analyzing internal activations to identify potential hallucinations [3]; activation steering to control generations [4]; and "Language Model Arithmetic" to compose biases for style, vocab, etc [5]. But each also either requires tight integration with an LLM inference/serving engine (to access…

Paper and discussion history. A mention is not an endorsement.

WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia — mentioned by mcpackieh

Mon, 17 Jul 2023 16:49:39 GMT

esjeon is simply wrong; this study is not touting the accuracy of wikipedia's knowledge. It's touting their bot's ability to accurately convey wikipedia's knowledge. It's very much about the qualities of their bot, not the qualities of wikipedia. https://arxiv.org/pdf/2305.14292.pdf

Paper and discussion history. A mention is not an endorsement.

WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia — mentioned by dr_dshiv

Mon, 17 Jul 2023 15:26:03 GMT

Here is a direct link to the arxiv article: https://arxiv.org/abs/2305.14292 WikiChat: A Few-Shot LLM-Based Chatbot Grounded with Wikipedia

Paper and discussion history. A mention is not an endorsement.

WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia — mentioned by the_af

Mon, 17 Jul 2023 14:15:35 GMT

Easy-peasy, here's the citation: https://arxiv.org/abs/2305.14292 Looks like a legit paper.

Paper and discussion history. A mention is not an endorsement.

WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia — mentioned by sebzim4500

Mon, 17 Jul 2023 13:57:25 GMT

Can someone update the link to https://arxiv.org/abs/2305.14292 ? The headline refers to only a small portion of the linked page.

Paper and discussion history. A mention is not an endorsement.

WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia — HN submission

Wed, 31 May 2023 00:05:25 GMT

WikiChat: A Few-Shot LLM-Based Chatbot Grounded with Wikipedia

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.