{"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/teaching-language-models-to-evolve-with-users","title":"Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignment","arxiv_id":"2505.15456","date":"2025-05-21","proceeding":null,"authors":["Weixiang Zhao","Xingyu Sui","Yulin Hu","Jiahe Guo","Haixiao Liu","Biye Li","Yanyan Zhao","Bing Qin","Ting Liu"],"abstract":"Personalized alignment is essential for enabling large language models (LLMs) to engage effectively in user-centric dialogue. While recent prompt-based and offline optimization methods offer preliminary solutions, they fall short in cold-start scenarios and long-term personalization due to their inherently static and shallow designs. In this work, we introduce the Reinforcement Learning for Personalized Alignment (RLPA) framework, in which an LLM interacts with a simulated user model to iteratively infer and refine user profiles through dialogue. The training process is guided by a dual-level reward structure: the Profile Reward encourages accurate construction of user representations, while the Response Reward incentivizes generation of responses consistent with the inferred profile. We instantiate RLPA by fine-tuning Qwen-2.5-3B-Instruct, resulting in Qwen-RLPA, which achieves state-of-the-art performance in personalized dialogue. Empirical evaluations demonstrate that Qwen-RLPA consistently outperforms prompting and offline fine-tuning baselines, and even surpasses advanced commercial models such as Claude-3.5 and GPT-4o. Further analysis highlights Qwen-RLPA's robustness in reconciling conflicting user preferences, sustaining long-term personalization and delivering more efficient inference compared to recent reasoning-focused LLMs. These results emphasize the potential of dynamic profile inference as a more effective paradigm for building personalized dialogue systems.","url_abs":"https://arxiv.org/abs/2505.15456v1","url_pdf":"https://arxiv.org/pdf/2505.15456v1.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":[],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2505.15456","atlas_url":"https://app.syntology.ai/?focus=2505.15456","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.15456"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2505.15456"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2505.15456"},"call":"get_harvested_code_for_paper(arxiv_id=\"2505.15456\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2505.15456"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2505.15456\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2505.15456"},"call":"get_concepts_for_paper(arxiv_id=\"2505.15456\")"}],"by_repo":[{"repo":"XingYuSSS/RLPA","kind":"found_in_text","samples":8,"ran":4,"instrument":1,"unverified":4}],"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","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2505.15456.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2505.15456.svg"},"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/XingYuSSS/RLPA","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"ran_fixture":1,"unverified":4},"n_samples":8,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":4,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"found_in_text":{"samples":8,"ran":4,"n_ran_checked":3,"n_instrument":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,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":4,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-24","last":"2026-09-26","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"95084b4b49902e3d","code_sha256_prefix":"95084b4b49902e3d","entry":"compute_approx_kl","repo":"XingYuSSS/RLPA","repo_kind":"found_in_text","path":"openrlhf/models/utils.py","file_url":"https://github.com/XingYuSSS/RLPA/blob/HEAD/openrlhf/models/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"log_probs:Tensor/2/float, log_probs_base:Tensor/2/float, action_mask:Tensor/2/float, kl_estimator:str/0/str","fixture_out_type":"Tensor","level_recorded_at":"2026-09-26T01:55:17.694675+00:00","code_page":"/code/compute-approx-kl","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"95084b4b49902e3d"}},{"code_sha256":"b865f2e32571acf0","code_sha256_prefix":"b865f2e32571acf0","entry":"extract_profile_response","repo":"XingYuSSS/RLPA","repo_kind":"found_in_text","path":"scirpts/multi_turn_rfn.py","file_url":"https://github.com/XingYuSSS/RLPA/blob/HEAD/scirpts/multi_turn_rfn.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"response:str/0/str","fixture_out_type":"tuple","level_recorded_at":"2026-09-25T00:28:05.031210+00:00","retrieve_with":{"tool":"get_code","code_sha256":"b865f2e32571acf0"},"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b865f2e32571acf0"}},{"code_sha256":"75afa2affd2a8e36","code_sha256_prefix":"75afa2affd2a8e36","entry":"log_probs_from_logits","repo":"XingYuSSS/RLPA","repo_kind":"found_in_text","path":"openrlhf/models/utils.py","file_url":"https://github.com/XingYuSSS/RLPA/blob/HEAD/openrlhf/models/utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"logits:Tensor/3/float, labels:Tensor/2/int, temperature:float/0/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/log-probs-from-logits","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"75afa2affd2a8e36"}},{"code_sha256":"ca3514c46a1261d7","code_sha256_prefix":"ca3514c46a1261d7","entry":"strip_sequence","repo":"XingYuSSS/RLPA","repo_kind":"found_in_text","path":"openrlhf/cli/serve_rm.py","file_url":"https://github.com/XingYuSSS/RLPA/blob/HEAD/openrlhf/cli/serve_rm.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"text:str/0/str, pad_token:str/0/str, eos_token:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-26T03:58:20.443611+00:00","retrieve_with":{"tool":"get_code","code_sha256":"ca3514c46a1261d7"},"code_page":"/code/strip-sequence","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ca3514c46a1261d7"}},{"code_sha256":"0d27f3b8c425d79f","code_sha256_prefix":"0d27f3b8c425d79f","entry":"compute_reward","repo":"XingYuSSS/RLPA","repo_kind":"found_in_text","path":"openrlhf/models/utils.py","file_url":"https://github.com/XingYuSSS/RLPA/blob/HEAD/openrlhf/models/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/compute-reward","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"0d27f3b8c425d79f"}},{"code_sha256":"d66f259aaf6cd9c7","code_sha256_prefix":"d66f259aaf6cd9c7","entry":"convert_ring_attn_params","repo":"XingYuSSS/RLPA","repo_kind":"found_in_text","path":"openrlhf/models/ring_attn_utils.py","file_url":"https://github.com/XingYuSSS/RLPA/blob/HEAD/openrlhf/models/ring_attn_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/convert-ring-attn-params","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"d66f259aaf6cd9c7"}},{"code_sha256":"b26627fa753393a8","code_sha256_prefix":"b26627fa753393a8","entry":"pad_sequences","repo":"XingYuSSS/RLPA","repo_kind":"found_in_text","path":"openrlhf/models/ring_attn_utils.py","file_url":"https://github.com/XingYuSSS/RLPA/blob/HEAD/openrlhf/models/ring_attn_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/pad-sequences","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b26627fa753393a8"}},{"code_sha256":"e93117d99aa6b210","code_sha256_prefix":"e93117d99aa6b210","entry":"reset_ring_attn_position_ids","repo":"XingYuSSS/RLPA","repo_kind":"found_in_text","path":"openrlhf/models/ring_attn_utils.py","file_url":"https://github.com/XingYuSSS/RLPA/blob/HEAD/openrlhf/models/ring_attn_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/reset-ring-attn-position-ids","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"e93117d99aa6b210"}}]},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"158df6b219b2d7da259962fed93ee3fdab07caaf03190c0d729a80554f426963","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}