{"doi":"10.48550/arxiv.2502.00883","title":"SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters","abstract":"Existing preference optimization objectives for language model alignment require additional hyperparameters that must be extensively tuned to achieve optimal performance, increasing both the complexity and time required for fine-tuning large language models. In this paper, we propose a simple yet effective hyperparameter-free preference optimization algorithm for alignment. We observe that promising performance can be achieved simply by optimizing inverse perplexity, which is calculated as the inverse of the exponentiated average log-likelihood of the chosen and rejected responses in the preference dataset. The resulting simple learning objective, SimPER, is easy to implement and eliminates the need for expensive hyperparameter tuning and a reference model, making it both computationally and memory efficient. Extensive experiments on widely used real-world benchmarks, including MT-Bench, AlpacaEval 2, and 10 key benchmarks of the Open LLM Leaderboard with 5 base models, demonstrate that SimPER consistently and significantly outperforms existing approaches-even without any hyperparameters or a reference model . For example, despite its simplicity, SimPER outperforms state-of-the-art methods by up to 5.7 points on AlpacaEval 2 and achieves the highest average ranking across 10 benchmarks on the Open LLM Leaderboard. The source code for SimPER is publicly available at: https://github.com/tengxiao1/SimPER.","journal":"arXiv (Cornell University)","year":2025,"id":561498,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":0,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9444,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2025-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1338754,"name":"Yige Yuan","orcid":"0000-0001-8038-3387","position":1,"is_corresponding":false},{"id":1463547,"name":"Zhengyu Chen","orcid":"0009-0003-8892-5699","position":2,"is_corresponding":false},{"id":1338753,"name":"Mingxiao Li","orcid":"0000-0003-0779-4432","position":3,"is_corresponding":false},{"id":1162352,"name":"Shangsong Liang","orcid":"0000-0003-1625-2168","position":4,"is_corresponding":false},{"id":1463548,"name":"Zhaochun Ren","orcid":"0000-0002-9076-6565","position":5,"is_corresponding":false},{"id":550147,"name":"Vasant Honavar","orcid":"0000-0001-5399-3489","position":6,"is_corresponding":false},{"id":1329842,"name":"Teng Xiao","orcid":null,"position":0,"is_corresponding":true}],"reference_count":0,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-07-19T02:55:58.259104Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}