{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/talk-like-a-graph-encoding-graphs-for-large","title":"Talk like a Graph: Encoding Graphs for Large Language Models","arxiv_id":"2310.04560","date":"2023-10-06","proceeding":null,"authors":["Bahare Fatemi","Jonathan Halcrow","Bryan Perozzi"],"abstract":"Graphs are a powerful tool for representing and analyzing complex relationships in real-world applications such as social networks, recommender systems, and computational finance. Reasoning on graphs is essential for drawing inferences about the relationships between entities in a complex system, and to identify hidden patterns and trends. Despite the remarkable progress in automated reasoning with natural text, reasoning on graphs with large language models (LLMs) remains an understudied problem. In this work, we perform the first comprehensive study of encoding graph-structured data as text for consumption by LLMs. We show that LLM performance on graph reasoning tasks varies on three fundamental levels: (1) the graph encoding method, (2) the nature of the graph task itself, and (3) interestingly, the very structure of the graph considered. These novel results provide valuable insight on strategies for encoding graphs as text. Using these insights we illustrate how the correct choice of encoders can boost performance on graph reasoning tasks inside LLMs by 4.8% to 61.8%, depending on the task.","url_abs":"https://arxiv.org/abs/2310.04560v1","url_pdf":"https://arxiv.org/pdf/2310.04560v1.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":"talk-like-a-graph-encoding-graphs-for-large","repo_url":"https://github.com/ChristianaKang11/google-graphqa","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"talk-like-a-graph-encoding-graphs-for-large","repo_url":"https://github.com/google-research/talk-like-a-graph","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"talk-like-a-graph-encoding-graphs-for-large","repo_url":"https://github.com/google-research/google-research/tree/master/graphqa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null}],"tasks":[{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.04560","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04560"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ChristianaKang11/google-graphqa","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google-research/talk-like-a-graph","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google-research/google-research/tree/master/graphqa","reach":null}],"summary":{"ran_draft_wrong":5},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1},"listed":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"80a181995f066599","entry":"add_edge_weight","repo":"ChristianaKang11/google-graphqa","repo_kind":"official","path":"graph_task.py","file_url":"https://github.com/ChristianaKang11/google-graphqa/blob/HEAD/graph_task.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"80a181995f066599"}},{"code_sha256_prefix":"9a4d3555abd9511d","entry":"generate_graphs","repo":"google-research/talk-like-a-graph","repo_kind":"listed","path":"talk_like_a_graph/graph_generators.py","file_url":"https://github.com/google-research/talk-like-a-graph/blob/HEAD/talk_like_a_graph/graph_generators.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9a4d3555abd9511d"}},{"code_sha256_prefix":"8d3fe6e5fe601ad1","entry":"has_edge_weights","repo":"ChristianaKang11/google-graphqa","repo_kind":"official","path":"graph_task.py","file_url":"https://github.com/ChristianaKang11/google-graphqa/blob/HEAD/graph_task.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8d3fe6e5fe601ad1"}},{"code_sha256_prefix":"89a2b6113ddd5c4c","entry":"randomize_directions","repo":"google-research/talk-like-a-graph","repo_kind":"listed","path":"talk_like_a_graph/graph_generators.py","file_url":"https://github.com/google-research/talk-like-a-graph/blob/HEAD/talk_like_a_graph/graph_generators.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"89a2b6113ddd5c4c"}},{"code_sha256_prefix":"2a7b9056d8a8ba8b","entry":"remove_graph_data","repo":"google-research/talk-like-a-graph","repo_kind":"listed","path":"talk_like_a_graph/graph_generators.py","file_url":"https://github.com/google-research/talk-like-a-graph/blob/HEAD/talk_like_a_graph/graph_generators.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2a7b9056d8a8ba8b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}