Lune

ACL Findings2025

Relevance Scores Calibration for Ranked List Truncation via TMP Adapter

Pavel Posokhov, Sergei Masliukhin, Stepan Skrylnikov, Danil Tirskikh, Olesia Makhnytkina

Abstract

The ranked list truncation task involves determining a truncation point to retrieve the relevant items from a ranked list. Despite current advancements, truncation methods struggle with limited capacity, unstable training and inconsistency of selected threshold. To address these problems we introduce TMP Adapter, a novel approach that builds upon the improved adapter model and incorporates the Threshold Margin Penalty (TMP) as an additive loss function to calibrate ranking model relevance scores for ranked list truncation. We evaluate TMP Adapter's performance on various retrieval datasets and observe that TMP Adapter is a promising advancement in the calibration methods, which offers both theoretical and practical benefits for ranked list truncation.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • List-aware Reranking-Truncation Joint Model for Search and Retrieval-augmented Generation cites Learning to Truncate Ranked Lists for Information Retrieval
  • List-aware Reranking-Truncation Joint Model for Search and Retrieval-augmented Generation cites Incorporating Retrieval Information into the Truncation of Ranking Lists for Better Legal Search
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on7

  1. SimLM: Pre-training with Representation Bottleneck for Dense Passage RetrievalLiang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao et al.ACL 2023 · 41 citations
  2. Incorporating Retrieval Information into the Truncation of Ranking Lists for Better Legal SearchYixiao Ma, Qingyao Ai, Yueyue Wu, Yunqiu Shao et al.SIGIR 2022 · 20 citations
  3. List-aware Reranking-Truncation Joint Model for Search and Retrieval-augmented GenerationShicheng Xu, Liang Pang, Jun Xu, Huawei Shen et al.WWW 2024 · 13 citations
  4. Threshold-Consistent Margin Loss for Open-World Deep Metric LearningQin Zhang, Linghan Xu, Jun Fang, Qingming Tang et al.ICLR 2024 · 10 citations
  5. Learning to Truncate Ranked Lists for Information RetrievalChen Wu, Ruqing Zhang, Jiafeng Guo, Yixing Fan et al.AAAI 2021 · 10 citations

Related papers

  1. MileCut: A Multi-view Truncation Framework for Legal Case RetrievalFuda Ye, Shuangyin LiWWW 2024 · 2 citations
  2. Logit Inflation in ListMLE: Theoretical Analysis and Mitigation StrategiesRiyaz Ahmad Bhat, Jaydeep SenSIGIR 2026
  3. AcuRank: Uncertainty-Aware Adaptive Computation for Listwise RerankingSoyoung Yoon, Gyuwan Kim, Gyu-Hwung Cho, Seung-won HwangNeurIPS 2025 · 15 citations
  4. Transfer-Aware Data Selection for Domain Adaptation in Text RetrievalLinzhu Yu, Huan Li, Ke Chen, Lidan ShouEMNLP Findings 2025
  5. Enhancing Document Ranking with Task-adaptive Training and Segmented Token Recovery MechanismXingwu Sun, Yanling Cui, Hongyin Tang, Fuzheng Zhang et al.EMNLP 2021 · 2 citations
Dusk over the sea between two cliffs drawn in fine vertical lines