Matches in SemOpenAlex for { <https://semopenalex.org/work/W4377372007> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W4377372007 abstract "Recent developments in large language models (LLMs) have been impressive. However, these models sometimes show inconsistencies and problematic behavior, such as hallucinating facts, generating flawed code, or creating offensive and toxic content. Unlike these models, humans typically utilize external tools to cross-check and refine their initial content, like using a search engine for fact-checking, or a code interpreter for debugging. Inspired by this observation, we introduce a framework called CRITIC that allows LLMs, which are essentially black boxes to validate and progressively amend their own outputs in a manner similar to human interaction with tools. More specifically, starting with an initial output, CRITIC interacts with appropriate tools to evaluate certain aspects of the text, and then revises the output based on the feedback obtained during this validation process. Comprehensive evaluations involving free-form question answering, mathematical program synthesis, and toxicity reduction demonstrate that CRITIC consistently enhances the performance of LLMs. Meanwhile, our research highlights the crucial importance of external feedback in promoting the ongoing self-improvement of LLMs." @default.
- W4377372007 created "2023-05-23" @default.
- W4377372007 creator A5034928588 @default.
- W4377372007 creator A5041448669 @default.
- W4377372007 creator A5042018181 @default.
- W4377372007 creator A5043356063 @default.
- W4377372007 creator A5051745436 @default.
- W4377372007 creator A5062703058 @default.
- W4377372007 creator A5085029347 @default.
- W4377372007 date "2023-05-19" @default.
- W4377372007 modified "2023-10-14" @default.
- W4377372007 title "CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing" @default.
- W4377372007 doi "https://doi.org/10.48550/arxiv.2305.11738" @default.
- W4377372007 hasPublicationYear "2023" @default.
- W4377372007 type Work @default.
- W4377372007 citedByCount "0" @default.
- W4377372007 crossrefType "posted-content" @default.
- W4377372007 hasAuthorship W4377372007A5034928588 @default.
- W4377372007 hasAuthorship W4377372007A5041448669 @default.
- W4377372007 hasAuthorship W4377372007A5042018181 @default.
- W4377372007 hasAuthorship W4377372007A5043356063 @default.
- W4377372007 hasAuthorship W4377372007A5051745436 @default.
- W4377372007 hasAuthorship W4377372007A5062703058 @default.
- W4377372007 hasAuthorship W4377372007A5085029347 @default.
- W4377372007 hasBestOaLocation W43773720071 @default.
- W4377372007 hasConcept C122783720 @default.
- W4377372007 hasConcept C127413603 @default.
- W4377372007 hasConcept C154945302 @default.
- W4377372007 hasConcept C168065819 @default.
- W4377372007 hasConcept C176856949 @default.
- W4377372007 hasConcept C177264268 @default.
- W4377372007 hasConcept C199360897 @default.
- W4377372007 hasConcept C2776760102 @default.
- W4377372007 hasConcept C41008148 @default.
- W4377372007 hasConcept C42475967 @default.
- W4377372007 hasConcept C98045186 @default.
- W4377372007 hasConceptScore W4377372007C122783720 @default.
- W4377372007 hasConceptScore W4377372007C127413603 @default.
- W4377372007 hasConceptScore W4377372007C154945302 @default.
- W4377372007 hasConceptScore W4377372007C168065819 @default.
- W4377372007 hasConceptScore W4377372007C176856949 @default.
- W4377372007 hasConceptScore W4377372007C177264268 @default.
- W4377372007 hasConceptScore W4377372007C199360897 @default.
- W4377372007 hasConceptScore W4377372007C2776760102 @default.
- W4377372007 hasConceptScore W4377372007C41008148 @default.
- W4377372007 hasConceptScore W4377372007C42475967 @default.
- W4377372007 hasConceptScore W4377372007C98045186 @default.
- W4377372007 hasLocation W43773720071 @default.
- W4377372007 hasOpenAccess W4377372007 @default.
- W4377372007 hasPrimaryLocation W43773720071 @default.
- W4377372007 hasRelatedWork W134747339 @default.
- W4377372007 hasRelatedWork W1498982577 @default.
- W4377372007 hasRelatedWork W1587224678 @default.
- W4377372007 hasRelatedWork W1601811574 @default.
- W4377372007 hasRelatedWork W2018297885 @default.
- W4377372007 hasRelatedWork W2209540864 @default.
- W4377372007 hasRelatedWork W2946801219 @default.
- W4377372007 hasRelatedWork W2947918972 @default.
- W4377372007 hasRelatedWork W4245681215 @default.
- W4377372007 hasRelatedWork W1937060886 @default.
- W4377372007 isParatext "false" @default.
- W4377372007 isRetracted "false" @default.
- W4377372007 workType "article" @default.