{"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/rilq-rank-insensitive-lora-based-quantization","title":"RILQ: Rank-Insensitive LoRA-based Quantization Error Compensation for Boosting 2-bit Large Language Model Accuracy","arxiv_id":"2412.01129","date":"2024-12-02","proceeding":null,"authors":["Geonho Lee","Janghwan Lee","Sukjin Hong","Minsoo Kim","Euijai Ahn","Du-Seong Chang","Jungwook Choi"],"abstract":"Low-rank adaptation (LoRA) has become the dominant method for parameter-efficient LLM fine-tuning, with LoRA-based quantization error compensation (LQEC) emerging as a powerful tool for recovering accuracy in compressed LLMs. However, LQEC has underperformed in sub-4-bit scenarios, with no prior investigation into understanding this limitation. We propose RILQ (Rank-Insensitive LoRA-based Quantization Error Compensation) to understand fundamental limitation and boost 2-bit LLM accuracy. Based on rank analysis revealing model-wise activation discrepancy loss's rank-insensitive nature, RILQ employs this loss to adjust adapters cooperatively across layers, enabling robust error compensation with low-rank adapters. Evaluations on LLaMA-2 and LLaMA-3 demonstrate RILQ's consistent improvements in 2-bit quantized inference across various state-of-the-art quantizers and enhanced accuracy in task-specific fine-tuning. RILQ maintains computational efficiency comparable to existing LoRA methods, enabling adapter-merged weight-quantized LLM inference with significantly enhanced accuracy, making it a promising approach for boosting 2-bit LLM performance. Our code is available at https://github.com/aiha-lab/RILQ.","url_abs":"https://arxiv.org/abs/2412.01129v3","url_pdf":"https://arxiv.org/pdf/2412.01129v3.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":"rilq-rank-insensitive-lora-based-quantization","repo_url":"https://github.com/aiha-lab/rilq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2412.01129","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.01129"}},"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/aiha-lab/rilq","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"official":{"samples":7,"ran":1,"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":"b5445674ab17410f","entry":"extract_alpaca_dataset","repo":"aiha-lab/rilq","repo_kind":"official","path":"rilq_utils/calib_data_loader.py","file_url":"https://github.com/aiha-lab/rilq/blob/HEAD/rilq_utils/calib_data_loader.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b5445674ab17410f"}},{"code_sha256_prefix":"13026bb5f6d06789","entry":"collate_data","repo":"aiha-lab/rilq","repo_kind":"official","path":"rilq_utils/data.py","file_url":"https://github.com/aiha-lab/rilq/blob/HEAD/rilq_utils/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"13026bb5f6d06789"}},{"code_sha256_prefix":"378e5dcfb3855a58","entry":"get_gt_loss","repo":"aiha-lab/rilq","repo_kind":"official","path":"rilq_utils/utils.py","file_url":"https://github.com/aiha-lab/rilq/blob/HEAD/rilq_utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"378e5dcfb3855a58"}},{"code_sha256_prefix":"0a74f9fd1675c6e9","entry":"get_logger","repo":"aiha-lab/rilq","repo_kind":"official","path":"rilq_utils/utils.py","file_url":"https://github.com/aiha-lab/rilq/blob/HEAD/rilq_utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0a74f9fd1675c6e9"}},{"code_sha256_prefix":"cdc4db6e5237cfc4","entry":"get_target_modules","repo":"aiha-lab/rilq","repo_kind":"official","path":"rilq_utils/utils.py","file_url":"https://github.com/aiha-lab/rilq/blob/HEAD/rilq_utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cdc4db6e5237cfc4"}},{"code_sha256_prefix":"0cfa46cd7236cebe","entry":"get_wikitext2","repo":"aiha-lab/rilq","repo_kind":"official","path":"rilq_utils/data.py","file_url":"https://github.com/aiha-lab/rilq/blob/HEAD/rilq_utils/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0cfa46cd7236cebe"}},{"code_sha256_prefix":"2379dffb2ba023d0","entry":"prepare_dataset","repo":"aiha-lab/rilq","repo_kind":"official","path":"rilq_utils/data.py","file_url":"https://github.com/aiha-lab/rilq/blob/HEAD/rilq_utils/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2379dffb2ba023d0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}