{"data":{"node":{"slug":"osu-nlp-group-llm-knowledge-conflict","name":"LLM-Knowledge-Conflict","tagline":"Examines behavior of large language models in knowledge conflicts using ConflictQA dataset","github_url":"https://github.com/OSU-NLP-Group/LLM-Knowledge-Conflict","owner":"OSU-NLP-Group","repo":"LLM-Knowledge-Conflict","owner_avatar_url":"https://avatars.githubusercontent.com/u/92067480?v=4","primary_language":"Python","stars":87,"forks":4,"topics":[],"archived":false,"github_pushed_at":"2024-04-12T06:38:36+00:00","maintenance_label":"Dormant","stars_delta_30d":3,"url":"https://www.graphcanon.com/tools/osu-nlp-group-llm-knowledge-conflict","markdown_url":"https://www.graphcanon.com/tools/osu-nlp-group-llm-knowledge-conflict.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/osu-nlp-group-llm-knowledge-conflict","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=osu-nlp-group-llm-knowledge-conflict"},"categories":[{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"},{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"}],"tags":[{"slug":"conflictqa","name":"conflictqa"},{"slug":"dataset","name":"dataset"},{"slug":"iclr-24","name":"iclr'24"},{"slug":"knowledge-conflict","name":"knowledge conflict"},{"slug":"large-language-models","name":"large-language-models"},{"slug":"llm-evaluation","name":"llm-evaluation"},{"slug":"parametric-memory","name":"parametric memory"}],"edges":[],"neighbours":[{"slug":"tencent-weknora","name":"WeKnora","tagline":"Open-source LLM knowledge platform for creating a queryable RAG, autonomous reasoning agent, and self-maintaining Wiki.","github_url":"https://github.com/Tencent/WeKnora","owner":"Tencent","repo":"WeKnora","owner_avatar_url":"https://avatars.githubusercontent.com/u/18461506?v=4","primary_language":"Go","stars":19992,"forks":2877,"topics":["agent","agentic","ai","chatbot","embeddings","evaluation","generative-ai","golang","knowledge-base","llm","multi-tenant","multimodel","ollama","openai","question-answering","rag","reranking","semantic-search","vector-search","wiki"],"archived":false,"github_pushed_at":"2026-08-16T05:31:52+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/tencent-weknora","markdown_url":"https://www.graphcanon.com/tools/tencent-weknora.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/tencent-weknora","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=tencent-weknora","shared_categories":["evaluation-observability"]},{"slug":"confident-ai-deepeval","name":"deepeval","tagline":"LLM Evaluation Framework.","github_url":"https://github.com/confident-ai/deepeval","owner":"confident-ai","repo":"deepeval","owner_avatar_url":"https://avatars.githubusercontent.com/u/130858411?v=4","primary_language":"Python","stars":18342,"forks":1953,"topics":["evaluation-framework","evaluation-metrics","llm-evaluation","llm-evaluation-framework","llm-evaluation-metrics","python"],"archived":false,"github_pushed_at":"2026-09-18T17:06:58+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/confident-ai-deepeval","markdown_url":"https://www.graphcanon.com/tools/confident-ai-deepeval.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/confident-ai-deepeval","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=confident-ai-deepeval","shared_categories":["evaluation-observability"]},{"slug":"rucaibox-llmsurvey","name":"LLMSurvey","tagline":"A collection of papers and resources related to Large Language Models","github_url":"https://github.com/RUCAIBox/LLMSurvey","owner":"RUCAIBox","repo":"LLMSurvey","owner_avatar_url":"https://avatars.githubusercontent.com/u/54706620?v=4","primary_language":"Python","stars":12216,"forks":930,"topics":["chain-of-thought","chatgpt","in-context-learning","instruction-tuning","large-language-models","llm","llms","natural-language-processing","pre-trained-language-models","pre-training","rlhf"],"archived":false,"github_pushed_at":"2025-03-11T09:51:42+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/rucaibox-llmsurvey","markdown_url":"https://www.graphcanon.com/tools/rucaibox-llmsurvey.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/rucaibox-llmsurvey","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=rucaibox-llmsurvey","shared_categories":[]},{"slug":"wangrongsheng-awesome-llm-resources","name":"awesome-LLM-resources","tagline":"Summary of the world's best LLM resources.","github_url":"https://github.com/WangRongsheng/awesome-LLM-resources","owner":"WangRongsheng","repo":"awesome-LLM-resources","owner_avatar_url":"https://avatars.githubusercontent.com/u/55651568?v=4","primary_language":null,"stars":8968,"forks":993,"topics":["awesome-list","book","course","large-language-models","llama","llm","mistral","openai","qwen","rag","retrieval-augmented-generation","webui"],"archived":false,"github_pushed_at":"2026-09-14T09:00:10+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/wangrongsheng-awesome-llm-resources","markdown_url":"https://www.graphcanon.com/tools/wangrongsheng-awesome-llm-resources.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/wangrongsheng-awesome-llm-resources","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=wangrongsheng-awesome-llm-resources","shared_categories":["evaluation-observability","data-retrieval"]},{"slug":"franxyao-chain-of-thought-hub","name":"chain-of-thought-hub","tagline":"Benchmarking large language models' complex reasoning ability with chain-of-thought prompting","github_url":"https://github.com/FranxYao/chain-of-thought-hub","owner":"FranxYao","repo":"chain-of-thought-hub","owner_avatar_url":"https://avatars.githubusercontent.com/u/17723677?v=4","primary_language":"Jupyter Notebook","stars":2776,"forks":144,"topics":[],"archived":false,"github_pushed_at":"2024-08-04T09:40:18+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/franxyao-chain-of-thought-hub","markdown_url":"https://www.graphcanon.com/tools/franxyao-chain-of-thought-hub.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/franxyao-chain-of-thought-hub","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=franxyao-chain-of-thought-hub","shared_categories":["evaluation-observability"]},{"slug":"harleyszhang-llm-note","name":"llm_note","tagline":"LLM notes covering model inference transformer structures and framework analysis","github_url":"https://github.com/harleyszhang/llm_note","owner":"harleyszhang","repo":"llm_note","owner_avatar_url":"https://avatars.githubusercontent.com/u/37138671?v=4","primary_language":"Python","stars":890,"forks":89,"topics":["cuda-programming","kv-cache","llm","llm-inference","transformer-models","triton-kernels","vllm"],"archived":false,"github_pushed_at":"2026-08-19T06:46:41+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/harleyszhang-llm-note","markdown_url":"https://www.graphcanon.com/tools/harleyszhang-llm-note.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/harleyszhang-llm-note","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=harleyszhang-llm-note","shared_categories":[]},{"slug":"declare-lab-instruct-eval","name":"instruct-eval","tagline":"Quantitative evaluation for instruction-tuned language models","github_url":"https://github.com/declare-lab/instruct-eval","owner":"declare-lab","repo":"instruct-eval","owner_avatar_url":"https://avatars.githubusercontent.com/u/59164695?v=4","primary_language":"Python","stars":553,"forks":45,"topics":["instruct-tuning","llm"],"archived":false,"github_pushed_at":"2024-03-10T05:00:00+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/declare-lab-instruct-eval","markdown_url":"https://www.graphcanon.com/tools/declare-lab-instruct-eval.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/declare-lab-instruct-eval","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=declare-lab-instruct-eval","shared_categories":["evaluation-observability"]},{"slug":"glgh-awesome-llm-human-preference-datasets","name":"awesome-llm-human-preference-datasets","tagline":"Curated list of Human Preference Datasets for LLM fine-tuning, RLHF, and eval","github_url":"https://github.com/glgh/awesome-llm-human-preference-datasets","owner":"glgh","repo":"awesome-llm-human-preference-datasets","owner_avatar_url":"https://avatars.githubusercontent.com/u/16108776?v=4","primary_language":null,"stars":394,"forks":19,"topics":["awesome-list","datasets","eval","human-preferences","llm","machine-learning","nlp","rlhf"],"archived":false,"github_pushed_at":"2023-10-04T19:56:44+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/glgh-awesome-llm-human-preference-datasets","markdown_url":"https://www.graphcanon.com/tools/glgh-awesome-llm-human-preference-datasets.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/glgh-awesome-llm-human-preference-datasets","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=glgh-awesome-llm-human-preference-datasets","shared_categories":["evaluation-observability"]},{"slug":"jagilley-fact-checker","name":"fact-checker","tagline":"Fact-checking LLM outputs with self-ask","github_url":"https://github.com/jagilley/fact-checker","owner":"jagilley","repo":"fact-checker","owner_avatar_url":"https://avatars.githubusercontent.com/u/37783831?v=4","primary_language":"Jupyter Notebook","stars":314,"forks":39,"topics":["llm","python"],"archived":false,"github_pushed_at":"2023-10-23T21:08:13+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/jagilley-fact-checker","markdown_url":"https://www.graphcanon.com/tools/jagilley-fact-checker.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/jagilley-fact-checker","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=jagilley-fact-checker","shared_categories":["evaluation-observability"]},{"slug":"alopatenko-llmevaluation","name":"LLMEvaluation","tagline":"A comprehensive guide to LLM evaluation methods","github_url":"https://github.com/alopatenko/LLMEvaluation","owner":"alopatenko","repo":"LLMEvaluation","owner_avatar_url":"https://avatars.githubusercontent.com/u/7122933?v=4","primary_language":"HTML","stars":201,"forks":24,"topics":["evaluation","generative-ai-benchmarking","llm","llm-benchmarking","llm-evaluation"],"archived":false,"github_pushed_at":"2026-09-15T00:35:53+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/alopatenko-llmevaluation","markdown_url":"https://www.graphcanon.com/tools/alopatenko-llmevaluation.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/alopatenko-llmevaluation","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=alopatenko-llmevaluation","shared_categories":["evaluation-observability"]},{"slug":"logikon-ai-awesome-deliberative-prompting","name":"awesome-deliberative-prompting","tagline":"Curated collection of resources on deliberative prompting for reliable reasoning with LLMs","github_url":"https://github.com/logikon-ai/awesome-deliberative-prompting","owner":"logikon-ai","repo":"awesome-deliberative-prompting","owner_avatar_url":"https://avatars.githubusercontent.com/u/126686445?v=4","primary_language":null,"stars":123,"forks":7,"topics":["awesome","awesome-list","chain-of-thought","deliberation","generative-ai","large-language-models","prompt-engineering","reasoning"],"archived":true,"github_pushed_at":"2025-02-03T20:00:33+00:00","maintenance_label":"Archived","url":"https://www.graphcanon.com/tools/logikon-ai-awesome-deliberative-prompting","markdown_url":"https://www.graphcanon.com/tools/logikon-ai-awesome-deliberative-prompting.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/logikon-ai-awesome-deliberative-prompting","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=logikon-ai-awesome-deliberative-prompting","shared_categories":[]},{"slug":"rungalileo-hallucination-index","name":"hallucination-index","tagline":"Initiative to evaluate and rank popular LLMs based on hallucination propensity","github_url":"https://github.com/rungalileo/hallucination-index","owner":"rungalileo","repo":"hallucination-index","owner_avatar_url":"https://avatars.githubusercontent.com/u/81123343?v=4","primary_language":null,"stars":115,"forks":8,"topics":["hallucinations","large-language-models","llm","llm-evaluation","openai","rag","retrieval-augmented-generation"],"archived":false,"github_pushed_at":"2025-07-28T18:28:09+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/rungalileo-hallucination-index","markdown_url":"https://www.graphcanon.com/tools/rungalileo-hallucination-index.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/rungalileo-hallucination-index","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=rungalileo-hallucination-index","shared_categories":["evaluation-observability"]}]}}