{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/information-retrieval/papers/3","list_of":"/task/information-retrieval","task":"Information Retrieval","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":3,"pages_in_order":48,"rows_per_page":100,"rows":[201,300],"of":4740,"counts":{"archive_papers_tagged":4740,"with_a_code_link":1188,"where_syntology_ran_a_sample":191,"not_listed_spam_title":0,"listed":4740,"listed_where_code_ran":191,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":151,"every_run_a_failure_of_syntologys_instrument":40,"listed_with_a_run_with_no_instrument_failure":151,"listed_every_run_a_failure_of_syntologys_instrument":40,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/information-retrieval","prev":"/task/information-retrieval/papers/2","next":"/task/information-retrieval/papers/4","papers":[{"url":"/paper/small-models-big-tasks-an-exploratory","slug":"small-models-big-tasks-an-exploratory","title":"Small Models, Big Tasks: An Exploratory Empirical Study on Small Language Models for Function Calling","date":"2025-04-27","arxiv_id":"2504.19277","repositories_listed":1,"syntology":null},{"url":"/paper/feature-fusion-revisited-multimodal-ctr","slug":"feature-fusion-revisited-multimodal-ctr","title":"Feature Fusion Revisited: Multimodal CTR Prediction for MMCTR Challenge","date":"2025-04-26","arxiv_id":"2504.18961","repositories_listed":1,"syntology":null},{"url":"/paper/finbert-qa-financial-question-answering-with","slug":"finbert-qa-financial-question-answering-with","title":"FinBERT-QA: Financial Question Answering with pre-trained BERT Language Models","date":"2025-04-24","arxiv_id":"2505.00725","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-ell-0-sparsification-for-inference","slug":"exploring-ell-0-sparsification-for-inference","title":"Exploring $\\ell_0$ Sparsification for Inference-free Sparse Retrievers","date":"2025-04-21","arxiv_id":"2504.14839","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/exploring-ell-0-sparsification-for-inference#ran","syntology_url":"https://syntology.ai/paper/2504.14839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.14839"}},"official":{"repos":["zhichao-aws/opensearch-sparse-model-tuning-sample"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/retrieval-augmented-generation-evaluation-in","slug":"retrieval-augmented-generation-evaluation-in","title":"Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Survey","date":"2025-04-21","arxiv_id":"2504.14891","repositories_listed":1,"syntology":null},{"url":"/paper/llm-driven-usefulness-judgment-for-web-search","slug":"llm-driven-usefulness-judgment-for-web-search","title":"LLM-Driven Usefulness Judgment for Web Search Evaluation","date":"2025-04-19","arxiv_id":"2504.14401","repositories_listed":1,"syntology":null},{"url":"/paper/template-based-financial-report-generation-in","slug":"template-based-financial-report-generation-in","title":"Template-Based Financial Report Generation in Agentic and Decomposed Information Retrieval","date":"2025-04-19","arxiv_id":"2504.14233","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-the-potential-for-large-language","slug":"exploring-the-potential-for-large-language","title":"Exploring the Potential for Large Language Models to Demonstrate Rational Probabilistic Beliefs","date":"2025-04-18","arxiv_id":"2504.13644","repositories_listed":1,"syntology":null},{"url":"/paper/building-russian-benchmark-for-evaluation-of","slug":"building-russian-benchmark-for-evaluation-of","title":"Building Russian Benchmark for Evaluation of Information Retrieval Models","date":"2025-04-17","arxiv_id":"2504.12879","repositories_listed":1,"syntology":null},{"url":"/paper/a-human-ai-comparative-analysis-of-prompt","slug":"a-human-ai-comparative-analysis-of-prompt","title":"A Human-AI Comparative Analysis of Prompt Sensitivity in LLM-Based Relevance Judgment","date":"2025-04-16","arxiv_id":"2504.12408","repositories_listed":1,"syntology":null},{"url":"/paper/pneuma-leveraging-llms-for-tabular-data","slug":"pneuma-leveraging-llms-for-tabular-data","title":"Pneuma: Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End System","date":"2025-04-12","arxiv_id":"2504.09207","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-human-like-thinking-in-search","slug":"exploring-human-like-thinking-in-search","title":"Exploring Human-Like Thinking in Search Simulations with Large Language Models","date":"2025-04-10","arxiv_id":"2504.07570","repositories_listed":1,"syntology":null},{"url":"/paper/how-do-large-language-models-understand","slug":"how-do-large-language-models-understand","title":"How do Large Language Models Understand Relevance? A Mechanistic Interpretability Perspective","date":"2025-04-10","arxiv_id":"2504.07898","repositories_listed":1,"syntology":null},{"url":"/paper/reanimator-reanimate-retrieval-test","slug":"reanimator-reanimate-retrieval-test","title":"REANIMATOR: Reanimate Retrieval Test Collections with Extracted and Synthetic Resources","date":"2025-04-10","arxiv_id":"2504.07584","repositories_listed":1,"syntology":null},{"url":"/paper/safechat-a-framework-for-building-trustworthy","slug":"safechat-a-framework-for-building-trustworthy","title":"SafeChat: A Framework for Building Trustworthy Collaborative Assistants and a Case Study of its Usefulness","date":"2025-04-08","arxiv_id":"2504.07995","repositories_listed":1,"syntology":null},{"url":"/paper/stealthrank-llm-ranking-manipulation-via","slug":"stealthrank-llm-ranking-manipulation-via","title":"StealthRank: LLM Ranking Manipulation via Stealthy Prompt Optimization","date":"2025-04-08","arxiv_id":"2504.05804","repositories_listed":1,"syntology":null},{"url":"/paper/distillation-and-refinement-of-reasoning-in","slug":"distillation-and-refinement-of-reasoning-in","title":"Distillation and Refinement of Reasoning in Small Language Models for Document Re-ranking","date":"2025-04-04","arxiv_id":"2504.03947","repositories_listed":1,"syntology":null},{"url":"/paper/generative-ai-enhanced-financial-risk","slug":"generative-ai-enhanced-financial-risk","title":"Generative AI Enhanced Financial Risk Management Information Retrieval","date":"2025-04-04","arxiv_id":"2504.06293","repositories_listed":1,"syntology":null},{"url":"/paper/talk2x-an-open-source-toolkit-facilitating","slug":"talk2x-an-open-source-toolkit-facilitating","title":"Talk2X -- An Open-Source Toolkit Facilitating Deployment of LLM-Powered Chatbots on the Web","date":"2025-04-04","arxiv_id":"2504.03343","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-reproducibility-of-learned-sparse","slug":"on-the-reproducibility-of-learned-sparse","title":"On the Reproducibility of Learned Sparse Retrieval Adaptations for Long Documents","date":"2025-03-31","arxiv_id":"2503.23824","repositories_listed":1,"syntology":null},{"url":"/paper/lira-a-learning-based-query-aware-partition","slug":"lira-a-learning-based-query-aware-partition","title":"LIRA: A Learning-based Query-aware Partition Framework for Large-scale ANN Search","date":"2025-03-30","arxiv_id":"2503.23409","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-contrastive-learning-synthetic-data","slug":"beyond-contrastive-learning-synthetic-data","title":"Beyond Contrastive Learning: Synthetic Data Enables List-wise Training with Multiple Levels of Relevance","date":"2025-03-29","arxiv_id":"2503.23239","repositories_listed":1,"syntology":null},{"url":"/paper/bias-aware-agent-enhancing-fairness-in-ai","slug":"bias-aware-agent-enhancing-fairness-in-ai","title":"Bias-Aware Agent: Enhancing Fairness in AI-Driven Knowledge Retrieval","date":"2025-03-27","arxiv_id":"2503.21237","repositories_listed":1,"syntology":null},{"url":"/paper/genius-a-generative-framework-for-universal","slug":"genius-a-generative-framework-for-universal","title":"GENIUS: A Generative Framework for Universal Multimodal Search","date":"2025-03-25","arxiv_id":"2503.19868","repositories_listed":1,"syntology":null},{"url":"/paper/how-generative-ir-retrieves-documents","slug":"how-generative-ir-retrieves-documents","title":"Reverse-Engineering the Retrieval Process in GenIR Models","date":"2025-03-25","arxiv_id":"2503.19715","repositories_listed":1,"syntology":null},{"url":"/paper/dense-passage-retrieval-in-conversational","slug":"dense-passage-retrieval-in-conversational","title":"Dense Passage Retrieval in Conversational Search","date":"2025-03-21","arxiv_id":"2503.17507","repositories_listed":1,"syntology":null},{"url":"/paper/unihdsa-a-unified-relation-prediction","slug":"unihdsa-a-unified-relation-prediction","title":"UniHDSA: A Unified Relation Prediction Approach for Hierarchical Document Structure Analysis","date":"2025-03-20","arxiv_id":"2503.15893","repositories_listed":1,"syntology":null},{"url":"/paper/narrative-trails-a-method-for-coherent","slug":"narrative-trails-a-method-for-coherent","title":"Narrative Trails: A Method for Coherent Storyline Extraction via Maximum Capacity Path Optimization","date":"2025-03-19","arxiv_id":"2503.15681","repositories_listed":1,"syntology":null},{"url":"/paper/mes-rag-bringing-multi-modal-entity-storage","slug":"mes-rag-bringing-multi-modal-entity-storage","title":"MES-RAG: Bringing Multi-modal, Entity-Storage, and Secure Enhancements to RAG","date":"2025-03-17","arxiv_id":"2503.13563","repositories_listed":1,"syntology":null},{"url":"/paper/agent-enhanced-large-language-models-for","slug":"agent-enhanced-large-language-models-for","title":"Agent-Enhanced Large Language Models for Researching Political Institutions","date":"2025-03-14","arxiv_id":"2503.13524","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-outlining-heterogeneous-recursive","slug":"beyond-outlining-heterogeneous-recursive","title":"Beyond Outlining: Heterogeneous Recursive Planning for Adaptive Long-form Writing with Language Models","date":"2025-03-11","arxiv_id":"2503.08275","repositories_listed":1,"syntology":{"n":6,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":6,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/beyond-outlining-heterogeneous-recursive#ran","syntology_url":"https://syntology.ai/paper/2503.08275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.08275"}},"official":{"repos":["principia-ai/WriteHERE"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/multiconir-towards-multi-condition","slug":"multiconir-towards-multi-condition","title":"MultiConIR: Towards multi-condition Information Retrieval","date":"2025-03-11","arxiv_id":"2503.08046","repositories_listed":1,"syntology":null},{"url":"/paper/perplexity-trap-plm-based-retrievers-overrate","slug":"perplexity-trap-plm-based-retrievers-overrate","title":"Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity Documents","date":"2025-03-11","arxiv_id":"2503.08684","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/perplexity-trap-plm-based-retrievers-overrate#ran","syntology_url":"https://syntology.ai/paper/2503.08684","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.08684"}},"official":{"repos":["whydwelledonai/perplexity-trap"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-survey-of-large-language-model-empowered","slug":"a-survey-of-large-language-model-empowered","title":"A Survey of Large Language Model Empowered Agents for Recommendation and Search: Towards Next-Generation Information Retrieval","date":"2025-03-07","arxiv_id":"2503.05659","repositories_listed":1,"syntology":null},{"url":"/paper/the-effectiveness-of-large-language-models-in","slug":"the-effectiveness-of-large-language-models-in","title":"The Effectiveness of Large Language Models in Transforming Unstructured Text to Standardized Formats","date":"2025-03-04","arxiv_id":"2503.02650","repositories_listed":1,"syntology":null},{"url":"/paper/2503-00955","slug":"2503-00955","title":"SemViQA: A Semantic Question Answering System for Vietnamese Information Fact-Checking","date":"2025-03-02","arxiv_id":"2503.00955","repositories_listed":1,"syntology":null},{"url":"/paper/qilin-a-multimodal-information-retrieval","slug":"qilin-a-multimodal-information-retrieval","title":"Qilin: A Multimodal Information Retrieval Dataset with APP-level User Sessions","date":"2025-03-01","arxiv_id":"2503.00501","repositories_listed":1,"syntology":null},{"url":"/paper/deepretrieval-powerful-query-generation-for","slug":"deepretrieval-powerful-query-generation-for","title":"DeepRetrieval: Hacking Real Search Engines and Retrievers with Large Language Models via Reinforcement Learning","date":"2025-02-28","arxiv_id":"2503.00223","repositories_listed":1,"syntology":{"n":25,"n_ran":24,"n_constructed":0,"n_ran_checked":23,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":23,"n_pointer_only":0,"phrase":"24 ran (of which 0 constructed an object rather than computing a result; 23 with no instrument failure: 0 honoured, 0 violated, 23 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/deepretrieval-powerful-query-generation-for#ran","syntology_url":"https://syntology.ai/paper/2503.00223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.00223"}},"official":{"repos":["pat-jj/deepretrieval"],"state":"official (archive's flag): 24 ran","n_ran":24,"n_constructed":0,"n_ran_no_instrument_failure":23,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/bridging-legal-knowledge-and-ai-retrieval","slug":"bridging-legal-knowledge-and-ai-retrieval","title":"Bridging Legal Knowledge and AI: Retrieval-Augmented Generation with Vector Stores, Knowledge Graphs, and Hierarchical Non-negative Matrix Factorization","date":"2025-02-27","arxiv_id":"2502.20364","repositories_listed":1,"syntology":null},{"url":"/paper/rank1-test-time-compute-for-reranking-in","slug":"rank1-test-time-compute-for-reranking-in","title":"Rank1: Test-Time Compute for Reranking in Information Retrieval","date":"2025-02-25","arxiv_id":"2502.18418","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rank1-test-time-compute-for-reranking-in#ran","syntology_url":"https://syntology.ai/paper/2502.18418","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.18418"}},"official":{"repos":["orionw/rank1"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-hybrid-approach-to-information-retrieval","slug":"a-hybrid-approach-to-information-retrieval","title":"A Hybrid Approach to Information Retrieval and Answer Generation for Regulatory Texts","date":"2025-02-24","arxiv_id":"2502.16767","repositories_listed":1,"syntology":null},{"url":"/paper/llm-qe-improving-query-expansion-by-aligning","slug":"llm-qe-improving-query-expansion-by-aligning","title":"LLM-QE: Improving Query Expansion by Aligning Large Language Models with Ranking Preferences","date":"2025-02-24","arxiv_id":"2502.17057","repositories_listed":1,"syntology":null},{"url":"/paper/the-gigamidi-dataset-with-features-for","slug":"the-gigamidi-dataset-with-features-for","title":"The GigaMIDI Dataset with Features for Expressive Music Performance Detection","date":"2025-02-24","arxiv_id":"2502.17726","repositories_listed":1,"syntology":null},{"url":"/paper/wrong-answers-can-also-be-useful-plausibleqa","slug":"wrong-answers-can-also-be-useful-plausibleqa","title":"Wrong Answers Can Also Be Useful: PlausibleQA -- A Large-Scale QA Dataset with Answer Plausibility Scores","date":"2025-02-22","arxiv_id":"2502.16358","repositories_listed":1,"syntology":null},{"url":"/paper/judging-the-judges-a-collection-of-llm","slug":"judging-the-judges-a-collection-of-llm","title":"Judging the Judges: A Collection of LLM-Generated Relevance Judgements","date":"2025-02-19","arxiv_id":"2502.13908","repositories_listed":1,"syntology":null},{"url":"/paper/towards-text-image-interleaved-retrieval","slug":"towards-text-image-interleaved-retrieval","title":"Towards Text-Image Interleaved Retrieval","date":"2025-02-18","arxiv_id":"2502.12799","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/towards-text-image-interleaved-retrieval#ran","syntology_url":"https://syntology.ai/paper/2502.12799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.12799"}},"official":{"repos":["vec-ai/wikihow-tiir"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/vus-effective-and-efficient-accuracy-measures","slug":"vus-effective-and-efficient-accuracy-measures","title":"VUS: Effective and Efficient Accuracy Measures for Time-Series Anomaly Detection","date":"2025-02-18","arxiv_id":"2502.13318","repositories_listed":1,"syntology":null},{"url":"/paper/any-information-is-just-worth-one-single","slug":"any-information-is-just-worth-one-single","title":"Any Information Is Just Worth One Single Screenshot: Unifying Search With Visualized Information Retrieval","date":"2025-02-17","arxiv_id":"2502.11431","repositories_listed":1,"syntology":{"n":21,"n_ran":10,"n_constructed":7,"n_ran_checked":8,"n_instrument":2,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"10 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/any-information-is-just-worth-one-single#ran","syntology_url":"https://syntology.ai/paper/2502.11431","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.11431"}},"official":null}},{"url":"/paper/fairdiverse-a-comprehensive-toolkit-for-fair","slug":"fairdiverse-a-comprehensive-toolkit-for-fair","title":"FairDiverse: A Comprehensive Toolkit for Fair and Diverse Information Retrieval Algorithms","date":"2025-02-17","arxiv_id":"2502.11883","repositories_listed":1,"syntology":null},{"url":"/paper/nitibench-a-comprehensive-studies-of-llm","slug":"nitibench-a-comprehensive-studies-of-llm","title":"NitiBench: A Comprehensive Studies of LLM Frameworks Capabilities for Thai Legal Question Answering","date":"2025-02-15","arxiv_id":"2502.10868","repositories_listed":1,"syntology":null},{"url":"/paper/mask-enhanced-autoregressive-prediction-pay","slug":"mask-enhanced-autoregressive-prediction-pay","title":"Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn More","date":"2025-02-11","arxiv_id":"2502.07490","repositories_listed":1,"syntology":null},{"url":"/paper/gsm-infinite-how-do-your-llms-behave-over","slug":"gsm-infinite-how-do-your-llms-behave-over","title":"GSM-Infinite: How Do Your LLMs Behave over Infinitely Increasing Context Length and Reasoning Complexity?","date":"2025-02-07","arxiv_id":"2502.05252","repositories_listed":1,"syntology":null},{"url":"/paper/disrupt-your-research-using-generative-ai","slug":"disrupt-your-research-using-generative-ai","title":"Disrupt Your Research Using Generative AI Powered ScienceSage","date":"2025-02-06","arxiv_id":"2502.18479","repositories_listed":1,"syntology":null},{"url":"/paper/musical-score-following-using-statistical","slug":"musical-score-following-using-statistical","title":"Musical Score Following using Statistical Inference","date":"2025-02-06","arxiv_id":"2502.10426","repositories_listed":1,"syntology":null},{"url":"/paper/syntriever-how-to-train-your-retriever-with","slug":"syntriever-how-to-train-your-retriever-with","title":"Syntriever: How to Train Your Retriever with Synthetic Data from LLMs","date":"2025-02-06","arxiv_id":"2502.03824","repositories_listed":1,"syntology":null},{"url":"/paper/rankify-a-comprehensive-python-toolkit-for","slug":"rankify-a-comprehensive-python-toolkit-for","title":"Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generation","date":"2025-02-04","arxiv_id":"2502.02464","repositories_listed":1,"syntology":null},{"url":"/paper/scalable-softmax-is-superior-for-attention","slug":"scalable-softmax-is-superior-for-attention","title":"Scalable-Softmax Is Superior for Attention","date":"2025-01-31","arxiv_id":"2501.19399","repositories_listed":1,"syntology":null},{"url":"/paper/illusions-of-relevance-using-content","slug":"illusions-of-relevance-using-content","title":"Illusions of Relevance: Using Content Injection Attacks to Deceive Retrievers, Rerankers, and LLM Judges","date":"2025-01-30","arxiv_id":"2501.18536","repositories_listed":1,"syntology":null},{"url":"/paper/ramqa-a-unified-framework-for-retrieval","slug":"ramqa-a-unified-framework-for-retrieval","title":"RAMQA: A Unified Framework for Retrieval-Augmented Multi-Modal Question Answering","date":"2025-01-23","arxiv_id":"2501.13297","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-gpt-s-ability-as-a-judge-in-music","slug":"exploring-gpt-s-ability-as-a-judge-in-music","title":"Exploring GPT's Ability as a Judge in Music Understanding","date":"2025-01-22","arxiv_id":"2501.13261","repositories_listed":1,"syntology":null},{"url":"/paper/tflop-table-structure-recognition-framework","slug":"tflop-table-structure-recognition-framework","title":"TFLOP: Table Structure Recognition Framework with Layout Pointer Mechanism","date":"2025-01-21","arxiv_id":"2501.11800","repositories_listed":1,"syntology":null},{"url":"/paper/improved-ir-based-bug-localization-with","slug":"improved-ir-based-bug-localization-with","title":"Improved IR-based Bug Localization with Intelligent Relevance Feedback","date":"2025-01-17","arxiv_id":"2501.10542","repositories_listed":1,"syntology":null},{"url":"/paper/mechir-a-mechanistic-interpretability","slug":"mechir-a-mechanistic-interpretability","title":"MechIR: A Mechanistic Interpretability Framework for Information Retrieval","date":"2025-01-17","arxiv_id":"2501.10165","repositories_listed":1,"syntology":null},{"url":"/paper/cybermentor-ai-powered-learning-tool-platform","slug":"cybermentor-ai-powered-learning-tool-platform","title":"CyberMentor: AI Powered Learning Tool Platform to Address Diverse Student Needs in Cybersecurity Education","date":"2025-01-16","arxiv_id":"2501.09709","repositories_listed":1,"syntology":null},{"url":"/paper/kannolo-sweet-and-smooth-approximate-k","slug":"kannolo-sweet-and-smooth-approximate-k","title":"kANNolo: Sweet and Smooth Approximate k-Nearest Neighbors Search","date":"2025-01-10","arxiv_id":"2501.06121","repositories_listed":1,"syntology":null},{"url":"/paper/text2playlist-generating-personalized","slug":"text2playlist-generating-personalized","title":"Text2Playlist: Generating Personalized Playlists from Text on Deezer","date":"2025-01-10","arxiv_id":"2501.05894","repositories_listed":1,"syntology":null},{"url":"/paper/finding-needles-in-emb-a-dding-haystacks","slug":"finding-needles-in-emb-a-dding-haystacks","title":"Finding Needles in Emb(a)dding Haystacks: Legal Document Retrieval via Bagging and SVR Ensembles","date":"2025-01-09","arxiv_id":"2501.05018","repositories_listed":1,"syntology":null},{"url":"/paper/quantum-inspired-embeddings-projection-and","slug":"quantum-inspired-embeddings-projection-and","title":"Quantum-inspired Embeddings Projection and Similarity Metrics for Representation Learning","date":"2025-01-08","arxiv_id":"2501.04591","repositories_listed":1,"syntology":null},{"url":"/paper/taclr-a-scalable-and-efficient-retrieval","slug":"taclr-a-scalable-and-efficient-retrieval","title":"TACLR: A Scalable and Efficient Retrieval-based Method for Industrial Product Attribute Value Identification","date":"2025-01-07","arxiv_id":"2501.03835","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/taclr-a-scalable-and-efficient-retrieval#ran","syntology_url":"https://syntology.ai/paper/2501.03835","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.03835"}},"official":null}},{"url":"/paper/towards-reliable-testing-for-multiple","slug":"towards-reliable-testing-for-multiple","title":"Towards Reliable Testing for Multiple Information Retrieval System Comparisons","date":"2025-01-07","arxiv_id":"2501.03930","repositories_listed":1,"syntology":null},{"url":"/paper/length-aware-detr-for-robust-moment-retrieval","slug":"length-aware-detr-for-robust-moment-retrieval","title":"Length-Aware DETR for Robust Moment Retrieval","date":"2024-12-30","arxiv_id":"2412.20816","repositories_listed":1,"syntology":null},{"url":"/paper/personalized-dynamic-music-emotion","slug":"personalized-dynamic-music-emotion","title":"Personalized Dynamic Music Emotion Recognition with Dual-Scale Attention-Based Meta-Learning","date":"2024-12-26","arxiv_id":"2412.19200","repositories_listed":1,"syntology":null},{"url":"/paper/reversed-in-time-a-novel-temporal-emphasized","slug":"reversed-in-time-a-novel-temporal-emphasized","title":"Reversed in Time: A Novel Temporal-Emphasized Benchmark for Cross-Modal Video-Text Retrieval","date":"2024-12-26","arxiv_id":"2412.19178","repositories_listed":1,"syntology":null},{"url":"/paper/computational-analysis-of-yaredawi-yezema","slug":"computational-analysis-of-yaredawi-yezema","title":"Computational Analysis of Yaredawi YeZema Silt in Ethiopian Orthodox Tewahedo Church Chants","date":"2024-12-25","arxiv_id":"2412.18788","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-robustness-of-generative-information","slug":"on-the-robustness-of-generative-information","title":"On the Robustness of Generative Information Retrieval Models","date":"2024-12-25","arxiv_id":"2412.18768","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-fine-tuning-methodology-of-text","slug":"efficient-fine-tuning-methodology-of-text","title":"Efficient fine-tuning methodology of text embedding models for information retrieval: contrastive learning penalty (clp)","date":"2024-12-23","arxiv_id":"2412.17364","repositories_listed":1,"syntology":null},{"url":"/paper/aspire-assistive-system-for-performance","slug":"aspire-assistive-system-for-performance","title":"ASPIRE: Assistive System for Performance Evaluation in IR","date":"2024-12-20","arxiv_id":"2412.15759","repositories_listed":1,"syntology":null},{"url":"/paper/empra-embedding-perturbation-rank-attack","slug":"empra-embedding-perturbation-rank-attack","title":"EMPRA: Embedding Perturbation Rank Attack against Neural Ranking Models","date":"2024-12-20","arxiv_id":"2412.16382","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-hubness-in-multi-modal-retrieval","slug":"adversarial-hubness-in-multi-modal-retrieval","title":"Adversarial Hubness in Multi-Modal Retrieval","date":"2024-12-18","arxiv_id":"2412.14113","repositories_listed":1,"syntology":null},{"url":"/paper/air-bench-automated-heterogeneous-information","slug":"air-bench-automated-heterogeneous-information","title":"AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark","date":"2024-12-17","arxiv_id":"2412.13102","repositories_listed":1,"syntology":null},{"url":"/paper/clasp-contrastive-language-speech-pretraining","slug":"clasp-contrastive-language-speech-pretraining","title":"CLASP: Contrastive Language-Speech Pretraining for Multilingual Multimodal Information Retrieval","date":"2024-12-17","arxiv_id":"2412.13071","repositories_listed":1,"syntology":null},{"url":"/paper/cross-dialect-information-retrieval","slug":"cross-dialect-information-retrieval","title":"Cross-Dialect Information Retrieval: Information Access in Low-Resource and High-Variance Languages","date":"2024-12-17","arxiv_id":"2412.12806","repositories_listed":1,"syntology":null},{"url":"/paper/enabling-low-resource-language-retrieval","slug":"enabling-low-resource-language-retrieval","title":"Enabling Low-Resource Language Retrieval: Establishing Baselines for Urdu MS MARCO","date":"2024-12-17","arxiv_id":"2412.12997","repositories_listed":1,"syntology":null},{"url":"/paper/token-level-graphs-for-short-text","slug":"token-level-graphs-for-short-text","title":"Token-Level Graphs for Short Text Classification","date":"2024-12-17","arxiv_id":"2412.12754","repositories_listed":1,"syntology":null},{"url":"/paper/speechprune-context-aware-token-pruning-for","slug":"speechprune-context-aware-token-pruning-for","title":"SpeechPrune: Context-aware Token Pruning for Speech Information Retrieval","date":"2024-12-16","arxiv_id":"2412.12009","repositories_listed":1,"syntology":null},{"url":"/paper/quantifying-positional-biases-in-text","slug":"quantifying-positional-biases-in-text","title":"Quantifying Positional Biases in Text Embedding Models","date":"2024-12-13","arxiv_id":"2412.15241","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/quantifying-positional-biases-in-text#ran","syntology_url":"https://syntology.ai/paper/2412.15241","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.15241"}},"official":{"repos":["sgoel97/neurips-embedding-positional-bias"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/unsupervised-named-entity-disambiguation-for","slug":"unsupervised-named-entity-disambiguation-for","title":"Unsupervised Named Entity Disambiguation for Low Resource Domains","date":"2024-12-13","arxiv_id":"2412.10054","repositories_listed":1,"syntology":null},{"url":"/paper/learning-cluster-representatives-for","slug":"learning-cluster-representatives-for","title":"Learning Cluster Representatives for Approximate Nearest Neighbor Search","date":"2024-12-08","arxiv_id":"2412.05921","repositories_listed":1,"syntology":null},{"url":"/paper/fathomgpt-a-natural-language-interface-for","slug":"fathomgpt-a-natural-language-interface-for","title":"FathomGPT: A Natural Language Interface for Interactively Exploring Ocean Science Data","date":"2024-12-03","arxiv_id":"2412.02784","repositories_listed":1,"syntology":null},{"url":"/paper/rare-retrieval-augmented-reasoning","slug":"rare-retrieval-augmented-reasoning","title":"RARE: Retrieval-Augmented Reasoning Enhancement for Large Language Models","date":"2024-12-03","arxiv_id":"2412.02830","repositories_listed":1,"syntology":null},{"url":"/paper/lamra-large-multimodal-model-as-your-advanced","slug":"lamra-large-multimodal-model-as-your-advanced","title":"LamRA: Large Multimodal Model as Your Advanced Retrieval Assistant","date":"2024-12-02","arxiv_id":"2412.01720","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lamra-large-multimodal-model-as-your-advanced#ran","syntology_url":"https://syntology.ai/paper/2412.01720","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.01720"}},"official":null}},{"url":"/paper/2d-matryoshka-training-for-information","slug":"2d-matryoshka-training-for-information","title":"2D Matryoshka Training for Information Retrieval","date":"2024-11-26","arxiv_id":"2411.17299","repositories_listed":1,"syntology":null},{"url":"/paper/can-llms-be-good-graph-judger-for-knowledge","slug":"can-llms-be-good-graph-judger-for-knowledge","title":"Can LLMs be Good Graph Judge for Knowledge Graph Construction?","date":"2024-11-26","arxiv_id":"2411.17388","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/can-llms-be-good-graph-judger-for-knowledge#ran","syntology_url":"https://syntology.ai/paper/2411.17388","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17388"}},"official":{"repos":["hhy-huang/graphjudge"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-data-aware-distance-comparison","slug":"efficient-data-aware-distance-comparison","title":"Efficient Data-aware Distance Comparison Operations for High-Dimensional Approximate Nearest Neighbor Search","date":"2024-11-26","arxiv_id":"2411.17229","repositories_listed":1,"syntology":null},{"url":"/paper/multi-label-sequential-sentence","slug":"multi-label-sequential-sentence","title":"Multi-label Sequential Sentence Classification via Large Language Model","date":"2024-11-23","arxiv_id":"2411.15623","repositories_listed":1,"syntology":null},{"url":"/paper/open-amp-synthetic-data-framework-for-audio","slug":"open-amp-synthetic-data-framework-for-audio","title":"Open-Amp: Synthetic Data Framework for Audio Effect Foundation Models","date":"2024-11-22","arxiv_id":"2411.14972","repositories_listed":1,"syntology":null},{"url":"/paper/g-rag-knowledge-expansion-in-material-science","slug":"g-rag-knowledge-expansion-in-material-science","title":"G-RAG: Knowledge Expansion in Material Science","date":"2024-11-21","arxiv_id":"2411.14592","repositories_listed":1,"syntology":null},{"url":"/paper/tsprank-bridging-pairwise-and-listwise","slug":"tsprank-bridging-pairwise-and-listwise","title":"TSPRank: Bridging Pairwise and Listwise Methods with a Bilinear Travelling Salesman Model","date":"2024-11-18","arxiv_id":"2411.12064","repositories_listed":1,"syntology":null},{"url":"/paper/harnessing-multiple-llms-for-information","slug":"harnessing-multiple-llms-for-information","title":"Harnessing multiple LLMs for Information Retrieval: A case study on Deep Learning methodologies in Biodiversity publications","date":"2024-11-14","arxiv_id":"2411.09269","repositories_listed":1,"syntology":null},{"url":"/paper/a-large-scale-study-of-relevance-assessments","slug":"a-large-scale-study-of-relevance-assessments","title":"A Large-Scale Study of Relevance Assessments with Large Language Models: An Initial Look","date":"2024-11-13","arxiv_id":"2411.08275","repositories_listed":1,"syntology":null}],"record_sha256":"c2c46dcfb4992a1fa957251a7301b65c02808fdfbd1593afcbb64abfd27e05d6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}