{"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/knowledgeable-r1-policy-optimization-for","title":"Knowledgeable-r1: Policy Optimization for Knowledge Exploration in Retrieval-Augmented Generation","arxiv_id":"2506.05154","date":"2025-06-05","proceeding":null,"authors":["Chenyu Lin","Yilin Wen","Du Su","Fei Sun","Muhan Chen","Chenfu Bao","Zhonghou Lv"],"abstract":"Retrieval-augmented generation (RAG) is a mainstream method for improving performance on knowledge-intensive tasks. However,current RAG systems often place too much emphasis on retrieved contexts. This can lead to reliance on inaccurate sources and overlook the model's inherent knowledge, especially when dealing with misleading or excessive information. To resolve this imbalance, we propose Knowledgeable-r1 that using joint sampling and define multi policy distributions in knowledge capability exploration to stimulate large language models'self-integrated utilization of parametric and contextual knowledge. Experiments show that Knowledgeable-r1 significantly enhances robustness and reasoning accuracy in both parameters and contextual conflict tasks and general RAG tasks, especially outperforming baselines by 17.07% in counterfactual scenarios and demonstrating consistent gains across RAG tasks. Our code are available at https://github.com/lcy80366872/ knowledgeable-r1.","url_abs":"https://arxiv.org/abs/2506.05154v1","url_pdf":"https://arxiv.org/pdf/2506.05154v1.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":"knowledgeable-r1-policy-optimization-for","repo_url":"https://github.com/lcy80366872/knowledgeable-r1","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"rag","task_name":"RAG"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"retrieval-augmented-generation","task_name":"Retrieval-augmented Generation"},{"task_slug":null,"task_name":"counterfactual"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bart","method_name":"BART"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"rag","method_name":"RAG"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2506.05154","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.05154"}},"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":"deterministic:regex_extraction","url":"https://github.com/lcy80366872/knowledgeable-R1","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lcy80366872/knowledgeable-r1","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"unverified":2},"by_repo_kind":{"official":{"samples":5,"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":0,"samples":[{"code_sha256_prefix":"74058a584804bb52","entry":"calculate_metrics_for_dataset","repo":"lcy80366872/knowledgeable-r1","repo_kind":"official","path":"get_metric.py","file_url":"https://github.com/lcy80366872/knowledgeable-r1/blob/HEAD/get_metric.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"74058a584804bb52"}},{"code_sha256_prefix":"216d106095f0f128","entry":"create_summary_tables","repo":"lcy80366872/knowledgeable-r1","repo_kind":"official","path":"get_metric.py","file_url":"https://github.com/lcy80366872/knowledgeable-r1/blob/HEAD/get_metric.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"216d106095f0f128"}},{"code_sha256_prefix":"b05420ebe972b7e7","entry":"process_results_folder","repo":"lcy80366872/knowledgeable-r1","repo_kind":"official","path":"get_metric.py","file_url":"https://github.com/lcy80366872/knowledgeable-r1/blob/HEAD/get_metric.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b05420ebe972b7e7"}},{"code_sha256_prefix":"627247bc47104fec","entry":"get_rope_index","repo":"lcy80366872/knowledgeable-r1","repo_kind":"official","path":"verl/models/transformers/qwen2_vl.py","file_url":"https://github.com/lcy80366872/knowledgeable-r1/blob/HEAD/verl/models/transformers/qwen2_vl.py","link_basis":"first_harvest_node","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":"627247bc47104fec"}},{"code_sha256_prefix":"1e90bebc7c04c766","entry":"qwen2_vl_attn_forward","repo":"lcy80366872/knowledgeable-r1","repo_kind":"official","path":"verl/models/transformers/qwen2_vl.py","file_url":"https://github.com/lcy80366872/knowledgeable-r1/blob/HEAD/verl/models/transformers/qwen2_vl.py","link_basis":"first_harvest_node","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":"1e90bebc7c04c766"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}