{"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/sift-grounding-llm-reasoning-in-contexts-via","title":"SIFT: Grounding LLM Reasoning in Contexts via Stickers","arxiv_id":"2502.14922","date":"2025-02-19","proceeding":null,"authors":["Zihao Zeng","Xuyao Huang","Boxiu Li","Zhijie Deng"],"abstract":"This paper identifies the misinterpretation of the context can be a significant issue during the reasoning process of large language models, spanning from smaller models like Llama3.2-3B-Instruct to cutting-edge ones like DeepSeek-R1. For example, in the phrase \"10 dollars per kilo,\" LLMs might not recognize that \"per\" means \"for each,\" leading to calculation errors. We introduce a novel, post-training approach called **Stick to the Facts (SIFT)** to tackle this. SIFT leverages increasing inference-time compute to ground LLM reasoning in contexts. At the core of SIFT lies the *Sticker*, which is generated by the model itself to explicitly emphasize the key information within the context. Given the curated Sticker, SIFT generates two predictions -- one from the original query and one from the query augmented with the Sticker. If they differ, the Sticker is sequentially refined via *forward* optimization (to better align the extracted facts with the query) and *inverse* generation (to conform with the model's inherent tendencies) for more faithful reasoning outcomes. Studies across diverse models (from 3B to 100B+) and benchmarks (e.g., GSM8K, MATH-500) reveal consistent performance improvements. Notably, SIFT improves the pass@1 accuracy of DeepSeek-R1 on AIME2024 from 78.33% to **85.67**%, establishing a new state-of-the-art in the open-source community. The code is available at https://github.com/zhijie-group/SIFT.","url_abs":"https://arxiv.org/abs/2502.14922v1","url_pdf":"https://arxiv.org/pdf/2502.14922v1.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":"sift-grounding-llm-reasoning-in-contexts-via","repo_url":"https://github.com/zhijie-group/sift","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"gsm8k","task_name":"GSM8K"},{"task_slug":"math","task_name":"Math"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2502.14922","atlas_url":"https://app.syntology.ai/?focus=2502.14922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.14922"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/zhijie-group/sift","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":6,"ran":4,"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":0,"samples":[{"code_sha256_prefix":"ce5e8d183ef999fd","entry":"gsm8k_dataset_postprocess","repo":"zhijie-group/sift","repo_kind":"official","path":"acc_stage2.py","file_url":"https://github.com/zhijie-group/sift/blob/HEAD/acc_stage2.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ce5e8d183ef999fd"}},{"code_sha256_prefix":"c02f62651b2ec2e2","entry":"gsm8k_dataset_postprocess","repo":"zhijie-group/sift","repo_kind":"official","path":"gsm8k_compare_token_num_v2.py","file_url":"https://github.com/zhijie-group/sift/blob/HEAD/gsm8k_compare_token_num_v2.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c02f62651b2ec2e2"}},{"code_sha256_prefix":"c21204b1470e67aa","entry":"gsm8k_postprocess","repo":"zhijie-group/sift","repo_kind":"official","path":"acc_stage2.py","file_url":"https://github.com/zhijie-group/sift/blob/HEAD/acc_stage2.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c21204b1470e67aa"}},{"code_sha256_prefix":"90b5c896e5eaea5e","entry":"last_boxed_only_string","repo":"zhijie-group/sift","repo_kind":"official","path":"acc_stage2.py","file_url":"https://github.com/zhijie-group/sift/blob/HEAD/acc_stage2.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"90b5c896e5eaea5e"}},{"code_sha256_prefix":"58a6c47e6ced737b","entry":"download_dataset","repo":"zhijie-group/sift","repo_kind":"official","path":"datasets.py","file_url":"https://github.com/zhijie-group/sift/blob/HEAD/datasets.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"58a6c47e6ced737b"}},{"code_sha256_prefix":"68edb9734be2f8be","entry":"get_data_path","repo":"zhijie-group/sift","repo_kind":"official","path":"datasets.py","file_url":"https://github.com/zhijie-group/sift/blob/HEAD/datasets.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"68edb9734be2f8be"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}