# THUIR2 at NTCIR-16 Session Search (SS) Task

arXiv: https://arxiv.org/abs/2307.00250 · HTML: https://mlsanity.com/paper/2307.00250/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 9 references that are in the map.
- First posted on arXiv 1 Jul 2023.

## Builds on (most cited first, 3 of 3)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Overview of the TREC 2019 deep learning track](https://mlsanity.com/paper/2003.07820/) (2020)
- [Rethink Training of BERT Rerankers in Multi-Stage Retrieval Pipeline](https://mlsanity.com/paper/2101.08751/) (2021)

## Built on by (most cited first, 12 of 12)

- [Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models](https://mlsanity.com/paper/2403.06448/) (2024)
- [DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Models](https://mlsanity.com/paper/2403.10081/) (2024)
- [Parametric Retrieval Augmented Generation](https://mlsanity.com/paper/2501.15915/) (2025)
- [RbFT: Robust Fine-tuning for Retrieval-Augmented Generation against Retrieval Defects](https://mlsanity.com/paper/2501.18365/) (2025)
- [JuDGE: Benchmarking Judgment Document Generation for Chinese Legal System](https://mlsanity.com/paper/2503.14258/) (2025)
- [Mitigating Entity-Level Hallucination in Large Language Models](https://mlsanity.com/paper/2407.09417/) (2024)
- [SurGE: A Benchmark and Evaluation Framework for Scientific Survey Generation](https://mlsanity.com/paper/2508.15658/) (2025)
- [Wikiformer: Pre-training with Structured Information of Wikipedia for Ad-hoc Retrieval](https://mlsanity.com/paper/2312.10661/) (2023)
- [Joint Evaluation of Answer and Reasoning Consistency for Hallucination Detection in Large Reasoning Models](https://mlsanity.com/paper/2506.04832/) (2025)
- [LeKUBE: A Legal Knowledge Update BEnchmark](https://mlsanity.com/paper/2407.14192/) (2024)
- [STARD: A Chinese Statute Retrieval Dataset with Real Queries Issued by Non-professionals](https://mlsanity.com/paper/2406.15313/) (2024)
- [Towards Unification of Hallucination Detection and Fact Verification for Large Language Models](https://mlsanity.com/paper/2512.02772/) (2025)

## Abstract (arXiv)

Our team(THUIR2) participated in both FOSS and POSS subtasks of the NTCIR-161 Session Search (SS) Task. This paper describes our approaches and results. In the FOSS subtask, we submit five runs using learning-to-rank and fine-tuned pre-trained language models. We fine-tuned the pre-trained language model with ad-hoc data and session information and assembled them by a learning-to-rank method. The assembled model achieves the best performance among all participants in the preliminary evaluation. In the POSS subtask, we used an assembled model which also achieves the best performance in the preliminary evaluation.