# Temporal Preference Optimization for Unsupervised Retrieval

arXiv: https://arxiv.org/abs/2606.17664 · HTML: https://mlsanity.com/paper/2606.17664/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 40 of its 66 references that are in the map.
- First posted on arXiv 16 Jun 2026.

## Builds on (most cited first, 30 of 40)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Averaging Weights Leads to Wider Optima and Better Generalization](https://mlsanity.com/paper/1803.05407/) (2018)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [Latent Retrieval for Weakly Supervised Open Domain Question Answering](https://mlsanity.com/paper/1906.00300/) (2019)
- [A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.06211/) (2024)
- [Text and Code Embeddings by Contrastive Pre-Training](https://mlsanity.com/paper/2201.10005/) (2022)
- [Retrieval-Augmented Generation for AI-Generated Content: A Survey](https://mlsanity.com/paper/2402.19473/) (2024)
- [Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint](https://mlsanity.com/paper/2312.11456/) (2023)
- [Large Language Models for Information Retrieval: A Survey](https://mlsanity.com/paper/2308.07107/) (2023)
- [Time-Aware Language Models as Temporal Knowledge Bases](https://mlsanity.com/paper/2106.15110/) (2021)
- [RealTime QA: What's the Answer Right Now?](https://mlsanity.com/paper/2207.13332/) (2022)
- [Mind the Gap: Assessing Temporal Generalization in Neural Language Models](https://mlsanity.com/paper/2102.01951/) (2021)
- [Query Rewriting for Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2305.14283/) (2023)
- [Qualitatively characterizing neural network optimization problems](https://mlsanity.com/paper/1412.6544/) (2014)
- [Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints](https://mlsanity.com/paper/2309.16240/) (2023)
- [SituatedQA: Incorporating Extra-Linguistic Contexts into QA](https://mlsanity.com/paper/2109.06157/) (2021)
- [Dense Text Retrieval based on Pretrained Language Models: A Survey](https://mlsanity.com/paper/2211.14876/) (2022)
- [Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization](https://mlsanity.com/paper/2212.10445/) (2022)
- [Time Waits for No One! Analysis and Challenges of Temporal Misalignment](https://mlsanity.com/paper/2111.07408/) (2021)
- [From Matching to Generation: A Survey on Generative Information Retrieval](https://mlsanity.com/paper/2404.14851/) (2024)
- [Temporal Adaptation of BERT and Performance on Downstream Document Classification: Insights from Social Media](https://mlsanity.com/paper/2104.08116/) (2021)
- [Time Masking for Temporal Language Models](https://mlsanity.com/paper/2110.06366/) (2021)

## Abstract (arXiv)

Unsupervised dense retrievers offer scalability by learning semantic similarity from unlabeled documents via contrastive learning, but they struggle to capture the temporal relevance, retrieving semantically related but temporally misaligned documents-an important aspect when a document collection spans multiple time periods (e.g., retrieving documents from 2018-2025 for "Who is the president in 2019?" introduces temporal ambiguity). Existing methods rely on supervised training with explicit timestamps, which are not always feasible. We propose TPOUR (Temporal Preference Optimization for Unsupervised Retriever), which uses our novel training method Temporal Retrieval Preference Optimization (TRPO). TRPO reinterprets preference learning in the temporal dimension, guiding the retriever to favor temporally aligned documents. TPOUR further generalizes to unseen time periods via interpolation in a learned time embedding, enabling continuous temporal alignment. Experiments on temporal information retrieval (T-IR), TPOUR outperforms both unsupervised and supervised baselines. Compared to Qwen-Embedding-8B, despite being about 72.7x smaller, TPOUR Contriever improves average nDCG@5 by +4.04 (+12.15%) on explicit and +4.98 (+15.21%) on implicit queries. We provide our code at https://github.com/agwaBom/TPOUR.