Temporal Preference Optimization for Unsupervised Retrieval

• URL: http://arxiv.org/abs/2606.17664v1
• Date: Tue, 16 Jun 2026 08:27:22 GMT
• Title: Temporal Preference Optimization for Unsupervised Retrieval
• Abstract summary: We propose TPOUR (Temporal Preference Optimization for Unsupervised Retriever), which uses our novel training method Temporal Retrieval Preference Optimization (TRPO)<n>TPOUR generalizes to unseen time periods via in a learned time embedding, enabling continuous temporal alignment.<n>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.
• Score: 11.583736130556611
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Which Histories Matter for Time Series Forecasting? Learning Predictive Relevance with Future Supervision [0.0]
  A normalized-pattern retriever learns a listwise future-compatibility target while keeping inference-time scoring strictly past-only.<n>Our method retains similarity-based candidate generation but reranks its candidates by a more predictive relevance criterion.<n>Across six benchmarks, the reranker improves Pattern retrieval while revealing candidate-global, query-specific, and mixed relevance regimes.
  arXiv  Detail & Related papers  (2026-08-24T13:15:29Z)
• Learning Probabilistic Embeddings for Unsupervised Action Segmentation [28.558361258499527]
  We study the problem of unsupervised temporal action segmentation for long, untrimmed videos.<n>We learn a probabilistic embedding for frame representations.<n>Compared to baselines with deterministic embeddings, our approach improves MoF up to 20.7% and F1-score up to 19.0%.
  arXiv  Detail & Related papers  (2026-07-06T16:10:25Z)
• FRESCO: Benchmarking and Optimizing Re-rankers for Evolving Semantic Conflict in Retrieval-Augmented Generation [73.22935457705057]
  We introduce FRESCO, a benchmark for evaluating re-rankers in temporally dynamic contexts.<n>By pairing recency-seeking queries with historical Wikipedia revisions, FRESCO tests whether re-rankers can prioritize factually recent evidence while maintaining semantic relevance.<n>Our evaluation reveals a consistent failure mode across existing re-rankers: a strong bias toward older, semantically rich documents, even when they are factually obsolete.
  arXiv  Detail & Related papers  (2026-04-14T17:04:25Z)
• ImpliRet: Benchmarking the Implicit Fact Retrieval Challenge [50.93758649363798]
  Impliret is a benchmark that shifts the reasoning challenge to document-side processing.<n>We evaluate a range of sparse and dense retrievers, all of which struggle in this setting.
  arXiv  Detail & Related papers  (2025-06-17T11:08:29Z)
• Maximally-Informative Retrieval for State Space Model Generation [59.954191072042526]
  We introduce Retrieval In-Context Optimization (RICO) to minimize model uncertainty for a particular query at test-time.<n>Unlike traditional retrieval-augmented generation (RAG), which relies on externals for document retrieval, our approach leverages direct feedback from the model.<n>We show that standard top-$k$ retrieval with model gradients can approximate our optimization procedure, and provide connections to the leave-one-out loss.
  arXiv  Detail & Related papers  (2025-06-13T18:08:54Z)
• A theoretical framework for self-supervised contrastive learning for continuous dependent data [79.62732169706054]
  Self-supervised learning (SSL) has emerged as a powerful approach to learning representations, particularly in the field of computer vision.<n>We propose a novel theoretical framework for contrastive SSL tailored to emphsemantic independence between samples.<n>Specifically, we outperform TS2Vec on the standard UEA and UCR benchmarks, with accuracy improvements of $4.17$% and $2.08$%, respectively.
  arXiv  Detail & Related papers  (2025-06-11T14:23:47Z)
• TempRetriever: Fusion-based Temporal Dense Passage Retrieval for Time-Sensitive Questions [18.87473448633352]
  We propose TempRetriever, which explicitly incorporates temporal information by embedding both the query date and document timestamp into the retrieval process.<n> TempRetriever achieves a 6.63% improvement in Top-1 retrieval accuracy and a 3.79% improvement in NDCG@10 compared to the standard DPR on ArchivalQA.<n>We also propose a novel, time-based negative sampling strategy which further enhances retrieval performance by addressing temporal misalignment during training.
  arXiv  Detail & Related papers  (2025-02-28T13:06:25Z)
• Gumbel Reranking: Differentiable End-to-End Reranker Optimization [61.16471123356738]
  RAG systems rely on rerankers to identify relevant documents.<n> fine-tuning these models remains challenging due to the scarcity of annotated query-document pairs.<n>We propose Gumbel Reranking, an end-to-end training framework for rerankers aimed at minimizing the training-inference gap.
  arXiv  Detail & Related papers  (2025-02-16T13:23:39Z)
• Temporal Sequencing of Documents [0.0]
  We outline an unsupervised method for temporal rank ordering of sets of historical documents. Our method relies upon capturing the gradual change in word usage via a bandwidth estimate. This unsupervised approach should enable the temporal ordering of undated document sets.
  arXiv  Detail & Related papers  (2023-11-05T06:51:04Z)
• LaPraDoR: Unsupervised Pretrained Dense Retriever for Zero-Shot Text Retrieval [55.097573036580066]
  Experimental results show that LaPraDoR achieves state-of-the-art performance compared with supervised dense retrieval models. Compared to re-ranking, our lexicon-enhanced approach can be run in milliseconds (22.5x faster) while achieving superior performance.
  arXiv  Detail & Related papers  (2022-03-11T18:53:12Z)
• Tensor Decompositions for temporal knowledge base completion [18.09363207672722]
  We introduce new regularization schemes and present an extension of ComplEx (Trouillon et al., 2016) that achieves state-of-the-art performance. We also propose a new dataset for knowledge base completion constructed from Wikidata, larger than previous benchmarks by an order of magnitude.
  arXiv  Detail & Related papers  (2020-04-10T07:09:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.