{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/crafting-interpretable-embeddings-by-asking","title":"Crafting Interpretable Embeddings by Asking LLMs Questions","arxiv_id":"2405.16714","date":"2024-05-26","proceeding":null,"authors":["Vinamra Benara","Chandan Singh","John X. Morris","Richard Antonello","Ion Stoica","Alexander G. Huth","Jianfeng Gao"],"abstract":"Large language models (LLMs) have rapidly improved text embeddings for a growing array of natural-language processing tasks. However, their opaqueness and proliferation into scientific domains such as neuroscience have created a growing need for interpretability. Here, we ask whether we can obtain interpretable embeddings through LLM prompting. We introduce question-answering embeddings (QA-Emb), embeddings where each feature represents an answer to a yes/no question asked to an LLM. Training QA-Emb reduces to selecting a set of underlying questions rather than learning model weights. We use QA-Emb to flexibly generate interpretable models for predicting fMRI voxel responses to language stimuli. QA-Emb significantly outperforms an established interpretable baseline, and does so while requiring very few questions. This paves the way towards building flexible feature spaces that can concretize and evaluate our understanding of semantic brain representations. We additionally find that QA-Emb can be effectively approximated with an efficient model, and we explore broader applications in simple NLP tasks.","url_abs":"https://arxiv.org/abs/2405.16714v1","url_pdf":"https://arxiv.org/pdf/2405.16714v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"crafting-interpretable-embeddings-by-asking","repo_url":"https://github.com/csinva/interpretable-embeddings","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"crafting-interpretable-embeddings-by-asking","repo_url":"https://github.com/csinva/imodelsX","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"crafting-interpretable-embeddings-by-asking","repo_url":"https://github.com/microsoft/automated-explanations","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2405.16714","atlas_url":"https://app.syntology.ai/?focus=2405.16714","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2405.16714"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2405.16714\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2405.16714"},"call":"get_concepts_for_paper(arxiv_id=\"2405.16714\")"}],"by_repo":[{"repo":"csinva/interpretable-embeddings","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"csinva/imodelsX","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2210.01848"],"harvested_for_calls":[{"arxiv_id":"2210.01848","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2210.01848"},"call":"get_harvested_code_for_paper(arxiv_id=\"2210.01848\")"}]},{"repo":"microsoft/automated-explanations","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2410.00812"],"harvested_for_calls":[{"arxiv_id":"2410.00812","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2410.00812"},"call":"get_harvested_code_for_paper(arxiv_id=\"2410.00812\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"d26183f578f2105c84aa7c27ca392d77a04ac15ea627d3fbda594fa7ab0a284c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}