Abdelrahman Abdallah, Bhawna Piryani Universität Innsbruck, Jamshid Mozafari Universität Innsbruck, Andreas Herzinger Universität Innsbruck, Jamie Holdcroft, Adam Jatowt
Building retrieval-augmented generation (RAG) systems often requires combining separate tools for retrieval, re-ranking, and generation, with incompatible data formats, evaluation pipelines, and deployment workflows. We present Rankify, an open-source Python toolkit that unifies these stages in a single modular framework. Rankify provides 42 benchmark datasets with pre-retrieved documents and pre-built indices, 15 retrievers (sparse, dense, and reasoning-augmented), and 24 re-ranking models spanning 41 pointwise, pairwise, and listwise variants. It also supports 6 RAG strategies across four inference backends (Hugging Face, vLLM, LiteLLM, and OpenAI), enabling consistent experimentation from local models to hosted APIs. A unified pipeline interface allows users to compose retrieve–rerank–generate workflows in a few lines of code, while an agentic assistant (RankifyAgent), aREST server (RankifyServer), and an interactive web playground support deployment and non-programmatic exploration. Across 200+ configurations on QA and BEIR/TREC benchmarks with six generator LLMs, re-ranking consistently improves downstream performance, yielding gains of 5–15 points in Exact Match and up to 8.5 points in RAGAS context precision across diverse retriever–generator combinations. Rankify is released under the Apache-2.0 License.
尚无 AI 解读，展示原文摘要
cs.CL · cs.AI
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations) · 2026 · 正式发表
Bhawna Piryani Universität Innsbruck, Abdelrahman Abdallah, Jamshid Mozafari Universität Innsbruck, Avishek Anand Delft University of Technology, Adam Jatowt
Time plays a critical role in how information is generated, retrieved, and interpreted. In this survey, we provide a comprehensive overview of Temporal Question Answering (TQA), a research area that focuses on answering questions involving temporal constraints or context. As time-stamped content from sources like news articles, web archives, and knowledge bases continues to grow, TQA systems must address challenges such as detecting temporal intent, normalizing time expressions, ordering events, and reasoning over evolving or ambiguous facts. We organize existing work through a unified perspective that captures the interaction between corpus temporality, question temporality, and model capabilities, enabling a systematic comparison of datasets, tasks, and approaches. We review recent advances in TQA enabled by neural architectures, especially transformer-based models and Large Language Models (LLMs), highlighting progress in temporal language modeling, retrieval-augmented generation (RAG), and temporal reasoning. We also discuss benchmark datasets and evaluation strategies designed to test temporal robustness, recency awareness, and generalization.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Abdelrahman Abdallah, Mohammed Ali, Bhawna Piryani Universität Innsbruck, Adam Jatowt
Although Large Language Models (LLMs) show strong potential for zero-shot document ranking, current listwise approaches face three critical limitations. First, context length constraints prevent processing many documents simultaneously. Second, sequential generation creates bottlenecks that cannot run in parallel. Third, ranking results depend heavily on initial document order, leading to inconsistent performance. We introduce BracketRank, a reasoning-driven competitive elimination framework that addresses these challenges through systematic group competition. Our method uses adaptive grouping to automatically optimise group sizes based on LLM context limits, reasoning-enhanced prompts that require explicit relevance explanations, and bracket-style elimination where documents compete through winner and loser brackets. This structure ensures every document has fair advancement opportunities regardless of initial positioning while allowing for parallel processing across competition stages. We evaluate BracketRank on TREC DL 19, TREC DL 20, and eight BEIR benchmark datasets. Results show that BracketRank achieves 77.90 NDCG@5 on TREC DL 19 and 75.85 NDCG@5 on TREC DL 20, outperforming RankGPT and other state-of-the-art methods. On BEIR datasets, BracketRank reaches 54.66 average NDCG@10, demonstrating robust performance across diverse domains.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表