{"total":13,"items":[{"citing_arxiv_id":"2605.16479","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Policy-Grounded Dynamic Facet Suggestions for Job Search","primary_cat":"cs.IR","submitted_at":"2026-05-15T17:30:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A policy-grounded retrieval-augmented framework with SLM scoring generates real-time personalized facet suggestions that boost engagement and job search outcomes.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00560","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"When More Reformulations Hurt: Avoiding Drift using Ranker Feedback","primary_cat":"cs.IR","submitted_at":"2026-05-01T10:58:18+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"ReformIR adaptively prioritizes reformulations and documents with a surrogate model guided by ranker feedback to boost recall while suppressing drift under fixed reranking budgets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.27421","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Reproducibility Study of LLM-Based Query Reformulation","primary_cat":"cs.IR","submitted_at":"2026-04-30T04:51:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A unified evaluation finds LLM query reformulation gains are strongly conditioned on retrieval paradigm, do not consistently transfer to neural retrievers, and are not uniformly improved by larger LLMs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.22661","ref_index":45,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Can QPP Choose the Right Query Variant? Evaluating Query Variant Selection for RAG Pipelines","primary_cat":"cs.IR","submitted_at":"2026-04-24T15:36:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"QPP methods can select query variants that boost end-to-end RAG quality over the original query, though retrieval-optimized variants often fail to produce the best generated answers, revealing a utility gap.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.19685","ref_index":55,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"An Answer is just the Start: Related Insight Generation for Open-Ended Document-Grounded QA","primary_cat":"cs.CL","submitted_at":"2026-04-21T17:07:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"InsightGen uses thematic clustering and graph neighborhood selection to generate diverse, relevant insights for open-ended document-grounded questions and releases the SCOpE-QA dataset of 3000 questions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.07720","ref_index":14,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Towards Knowledgeable Deep Research: Framework and Benchmark","primary_cat":"cs.AI","submitted_at":"2026-04-09T02:06:27+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"The paper introduces the KDR task, HKA multi-agent framework, and KDR-Bench to enable LLM agents to integrate structured knowledge into deep research reports, with experiments showing outperformance over prior agents.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"consists of three main steps, namely, Intent Generation, Web Search, and Result Summarization. Intent Generation.Since the U.K.A. queries generated by the Planner are usually short and lack specific details, it is difficult to obtain precise information from massive web pages with only these queries. Therefore, we prompt the LLM to expand each U.K.A. query into a detailed search intent based on the current subtask [14, 18], so that we can extract relevant information from web pages. Web Search.Based on the U.K.A. query and generated search in- tent, this sub-agent retrieves web pages through an existing search engine. Then, the sub-agent converts the web pages into Markdown, an LLM-friendly format. Result Summarization.Finally, the sub-agent summarizes rele- vant information, including key data, descriptions, and conclusions,"},{"citing_arxiv_id":"2602.17667","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"When & How to Write for Personalized Demand-aware Query Rewriting in Video Search","primary_cat":"cs.IR","submitted_at":"2025-12-17T07:00:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"WeWrite mines user logs to decide when personalization is needed and trains LLMs with SFT and GRPO to rewrite video search queries, delivering 1.07% more long-view clicks and 2.97% fewer reformulations in live A/B tests.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2512.06879","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"WisPaper: Your AI Scholar Search Engine","primary_cat":"cs.IR","submitted_at":"2025-12-07T15:10:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"WisPaper integrates semantic search with agent-based validation, library organization, and personalized AI feeds into a closed-loop system that improves academic paper discovery and long-term awareness.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.15408","ref_index":79,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Chinese Short-Form Creative Content Generation via Explanation-Oriented Multi-Objective Optimization","primary_cat":"cs.CL","submitted_at":"2025-11-19T13:05:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"MAGIC-HMO is a multi-agent framework that treats Chinese short-form creative NLG as heterogeneous multi-objective optimization over personalized constraints plus explanation reliability and outperforms baselines on a baby-naming benchmark.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2509.07794","ref_index":35,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Query Expansion in the Age of Pre-trained and Large Language Models: A Comprehensive Survey","primary_cat":"cs.IR","submitted_at":"2025-09-09T14:31:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A comprehensive survey that organizes query expansion methods in the PLM/LLM era along four design dimensions, synthesizes application patterns, and outlines future directions.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"PLM/LLM-Driven QE Techniques Point of injection Implicit Embedding-based QE: ANCE-PRF [123], ColBERT-PRF [109], Eclipse [22],QB-PRF [129], LLM-VPRF [56] Selection-based Explicit QE: CEQE [74], SQET [75], BERT-QE [132], CQED [39],PQEWC [10] Grounding and interaction Zero-Grounding, Non-Interactive QE: LLM-Driven Single-Stage Expansion:Query2Doc [107], CoT-QE [35], GAR [69], GRF [66], HyDE [29], Exp4Fuse [60],Contextual clue sampling and fusion [59], SEAL [12] Grounding-Only, Non-Interactive QE: Corpus-Evidence Anchored Single-Pass Expansion:MILL [36], AGR [18], EAR [19], GenPRF [108], CSQE [50], MUGI [127], PromptPRF [55],FGQE [34] Grounding-A ware Interactive QE: Multi-Round Retrieve-Expand Loops:InteR [26], ProQE [92], LameR [99], ThinkQE [51]"},{"citing_arxiv_id":"2502.00709","ref_index":24,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"RankFlow: A Multi-Role Collaborative Reranking Workflow Utilizing Large Language Models","primary_cat":"cs.IR","submitted_at":"2025-02-02T07:49:56+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"RankFlow deploys four LLM roles in sequence to rewrite queries, generate pseudo-answers, summarize passages, and rerank candidates, outperforming prior methods on TREC-DL, BEIR, and NovelEval.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2501.00309","ref_index":173,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","primary_cat":"cs.IR","submitted_at":"2024-12-31T06:59:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A survey proposing a holistic GraphRAG framework with components including query processor, retriever, organizer, generator, and data source, plus domain-tailored reviews, challenges, and future directions.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"topics; (2) queries may be too brief to fully capture user intent; and (3) users are often uncertain about what they are seeking. Generally, it can be categorized into manual query expansion, automatic query expansion, and interactive query expansion. More recently, LLM-based query expansion has been a prominent area due to the creativity of the generated content[54, 173, 221] Unlike existing methods that mostly focus on textual similarities and overlook relations, QE in GraphRAG augments LLM expansion with structured relations. For example Xia et al.[459] expands the query by leveraging neighboring nodes of the mentioned entities in the query. Alternatively, Wang et al. [406] convert the query into several sub-queries using pre-defined templates."},{"citing_arxiv_id":"2311.05232","ref_index":137,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","primary_cat":"cs.CL","submitted_at":"2023-11-09T09:25:37+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"[74] introduced the Chain-of-Verification (COVE), which operates under the assumption that, when appropriately prompted, LLMs can self-correct their mistakes and provide more accurate facts. Starting with an initial draft, it first formulates verification questions and then systematically answers those questions in order to finally produce an improved revised response. Similarly, Ji et al. [137] focused on the medical domain and introduced an iterative self-reflection process. This process leverages the inherent ability of LLMs to first generate factual knowledge and then refine the response until it aligns consistently with the provided background knowledge. Discussion. Factuality decoding methods, which typically assess the factuality at each decoding"}],"limit":50,"offset":0}