Papers › Selective Prompting Tuning for Personalized Conversations with LLMs

Selective Prompting Tuning for Personalized Conversations with LLMs

26 Jun 2024arXiv:2406.18187archive 2025-07-28

Qiushi Huang, Xubo Liu, Tom Ko, Bo Wu, Wenwu Wang, Yu Zhang, Lilian Tang

In conversational AI, personalizing dialogues with persona profiles and contextual understanding is essential. Despite large language models' (LLMs) improved response coherence, effective persona integration remains a challenge. In this work, we first study two common approaches for personalizing LLMs: textual prompting and direct fine-tuning. We observed that textual prompting often struggles to yield responses that are similar to the ground truths in datasets, while direct fine-tuning tends to produce repetitive or overly generic replies. To alleviate those issues, we propose Selective Prompt Tuning (SPT), which softly prompts LLMs for personalized conversations in a selective way. Concretely, SPT initializes a set of soft prompts and uses a trainable dense retriever to adaptively select suitable soft prompts for LLMs according to different input contexts, where the prompt retriever is dynamically updated through feedback from the LLMs. Additionally, we propose context-prompt contrastive learning and prompt fusion learning to encourage the SPT to enhance the diversity of personalized conversations. Experiments on the CONVAI2 dataset demonstrate that SPT significantly enhances response diversity by up to 90%, along with improvements in other critical performance indicators. Those results highlight the efficacy of SPT in fostering engaging and personalized dialogue generation. The SPT model code (https://github.com/hqsiswiliam/SPT) is publicly available for further exploration.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 16 code samples harvested from 1 repository linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 1 violated, 6 with no contract checked; 8 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 16 ran (8 with no instrument failure; 8 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

hqsiswiliam/SPT officialmentioned in paperpytorchSyntology: 16 samples, 16 ran (8 instrument-failed) · 0 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

16 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 1 violated, 6 with no contract checked; 8 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
8ran · our draft was wrong
6ran

Licence: 16 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from hqsiswiliam/SPT. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives 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” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

hqsiswiliam/SPT official repository 16 samples, 16 ran (8 instrument-failed) · 0 unverified
collate_fn in 500 papers dataset/dataset.py ran · our draft was wrong no licence file found · pointer only · 12321e4b78f02c35 · report fixture: signature sample_list:list/1/dict · returned dict · level recorded 2026-09-24
collate_fn_straight dataset/dataset.py ran · our draft was wrong no licence file found · pointer only · 56d9b66f17d0c5bb · report fixture: signature sample_list:list/1/dict · returned dict · level recorded 2026-09-24
collate_fn_straight_with_fn dataset/dataset.py ran · our draft was wrong no licence file found · pointer only · d40e134a2b264da2 · report fixture: signature fn:callable/0/? · returned function · level recorded 2026-09-24
combine_persona_query_response dataset/dataset_helper.py ran no licence file found · pointer only · 841580f6d198a94a · report fixture: signature persona:list/1/str, query:list/1/str, response:list/1/str, candidates:list/1/list · returned dict · level recorded 2026-09-25
em in 12 papers evaluation.py ran no licence file found · pointer only · 38c3b1ee62b65838 · report fixture: signature prediction:Tensor/1/float, ground_truth:Tensor/1/float, normalize_fn:callable/0/? · returned float · level recorded 2026-09-24
extend_compatibility_for_gated_transformer utils/config.py ran · our draft was wrong no licence file found · pointer only · db175d8c957ef116 · report fixture: signature configuration:MockConfiguration/0/? · returned MockConfiguration · level recorded 2026-09-24
f1 in 57 papers evaluation.py ran no licence file found · pointer only · 5e2f0b798a3d70d2 · report fixture: signature prediction:str/0/str, ground_truth:str/0/str, normalize_fn:callable/0/? · returned float · level recorded 2026-09-24
format_causal_personachat_input utils/format_inputs.py ran no licence file found · pointer only · d24e20215e8fb45f · report fixture: signature batch:dict/0/?, left_tokenizer:callable/0/?, right_tokenizer:callable/0/?, config:MockConfig/0/?, for_test:bool/0/bool, find_batch:bool/0/bool, template_type:int/0/int · returned tuple · level recorded 2026-09-24
format_generate_persona_input utils/format_inputs.py ran no licence file found · pointer only · 7b9bdfa46c029f5d · report fixture: signature batch:dict/0/?, left_tokenizer:callable/0/?, right_tokenizer:callable/0/?, config:MockConfig/0/?, for_test:bool/0/bool, find_batch:bool/0/bool · returned tuple · level recorded 2026-09-24
format_personachat_input utils/format_inputs.py ran no licence file found · pointer only · fd7ca588ae67fc72 · report fixture: signature batch:dict/0/?, left_tokenizer:callable/0/?, right_tokenizer:callable/0/?, config:MinimalConfig/0/?, for_test:bool/0/bool, find_batch:bool/0/bool · returned tuple · level recorded 2026-09-24
normalize_answer in 304 papers evaluation.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 6205dd62c2627dde · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-24
preprocess_text in 26 papers dataset/dataset_helper.py ran · our draft was wrong fingerprinted no licence file found · pointer only · f343f672c3ddd483 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-25
print_trainable_parameters in 9 papers utils/model_helpers.py ran · our draft was wrong no licence file found · pointer only · 062f390233bf4d6d · report fixture: signature model:callable/0/? · returned dict · level recorded 2026-09-24
read_personachat_split dataset/dataset_helper.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 64f0486dedc02e30 · report fixture: signature split_dir:str/0/str, only_longest:bool/0/bool · returned list · level recorded 2026-09-25
seed_everything in 16 papers utils/seed_everything.py ran · honoured contract fingerprinted no licence file found · pointer only · a73433deedbe1382 · report fixture: signature seed:int/0/int, workers:bool/0/bool · returned int · level recorded 2026-09-24
str2bool in 533 papers utils/parser_helper.py ran · violated contract no licence file found · pointer only · fe682fa7a99299d9 · report fixture: signature v:str/0/str · returned bool · level recorded 2026-09-24

Tasks

Contrastive LearningDialogue GenerationDiversity

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Contrastive LearningSET

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections