Source Viewer Tool & Result Confidence

tracking data lineage in tabular when using generative ai tools for sensitive life sciences applications, it is critical to understand where software responses come from, and if they are supported by source data reliant is built with data transparency, accuracy, and accountability at its core, and users always have access to source data via the source viewer tool source viewer tool when clicking any cell within a tabular result table, users will see the source viewer tab on the right side of the interface clicking this tab will open the source viewer pane tabular will search the source document and identify where it found the cell content additionally, users always have the option to open the source in its original format by clicking the icon in the top right of the source viewer pane in this case, this button links to a trial on clinicaltrials gov cell confidence score you’ll notice that in the above examples, there is a green box displaying “high confidence" score for each result cell, tabular generates a confidence score that measures how well the model thinks it addressed the given field/prompt for default, raw text columns that extract data that is directly defined in the source, (ex fda label indications, clinical trial start date, abstract pmid, etc ) the confidence level will be very high this is because the language model is not used to generate the result strings for cells that are created via an ai summary or generative ai prompt (see column types here for more information), the confidence of the response may vary based on the quality of relevant information in the source material, as well as the phrasing of the prompt itself for example, to the right is set of responses to a generative column created within a search table of active trials in hiv within each cell, the confidence is noted via an icon orange orange icons indicate medium confidence, while red red icons indicate low confidence tabular’s confidence ratings are conservative by design the software will err on the side of caution to avoid overstating accuracy to users we recommend using the source viewer pane for lower confidence outputs to understand how tabular is extracting data for a given prompt occasionally with low confidence answers, tabular can fail to find relevant information to highlight this is a good indication that the cell extraction is not supported by robust data, and users should be cautious if using this data without manual verification multiple identified answers when this icon appears in a cell, it indicates that tabular has identified multiple potential responses to this prompt within the source click on the icon to review each response initially, tabular will default to displaying the highest confidence response in the cell however, the user has the option to select the answer(s) they feel is most accurate if multiple responses are true, the user can split the selection into multiple rows to capture this data adding columns docid\ dq0rcozhbvzhjmok8ch3k