{"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/sentence/papers/8","list_of":"/task/sentence","task":"Sentence","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":8,"pages_in_order":108,"rows_per_page":100,"rows":[701,800],"of":10752,"counts":{"archive_papers_tagged":10752,"with_a_code_link":3811,"where_syntology_ran_a_sample":657,"not_listed_spam_title":0,"listed":10752,"listed_where_code_ran":657,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":544,"every_run_a_failure_of_syntologys_instrument":113,"listed_with_a_run_with_no_instrument_failure":544,"listed_every_run_a_failure_of_syntologys_instrument":113,"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/sentence","prev":"/task/sentence/papers/7","next":"/task/sentence/papers/9","papers":[{"url":"/paper/causal-graphical-models-for-vision-language","slug":"causal-graphical-models-for-vision-language","title":"Causal Graphical Models for Vision-Language Compositional Understanding","date":"2024-12-12","arxiv_id":"2412.09353","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/causal-graphical-models-for-vision-language#ran","syntology_url":"https://syntology.ai/paper/2412.09353","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.09353"}},"official":{"repos":["aimagelab/COGT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/large-concept-models-language-modeling-in-a","slug":"large-concept-models-language-modeling-in-a","title":"Large Concept Models: Language Modeling in a Sentence Representation Space","date":"2024-12-11","arxiv_id":"2412.08821","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/large-concept-models-language-modeling-in-a#ran","syntology_url":"https://syntology.ai/paper/2412.08821","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.08821"}},"official":{"repos":["facebookresearch/large_concept_model"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/can-linguists-better-understand-dna","slug":"can-linguists-better-understand-dna","title":"Can linguists better understand DNA?","date":"2024-12-10","arxiv_id":"2412.07678","repositories_listed":1,"syntology":null},{"url":"/paper/gear-a-simple-generate-embed-average-and-rank","slug":"gear-a-simple-generate-embed-average-and-rank","title":"GEAR: A Simple GENERATE, EMBED, AVERAGE AND RANK Approach for Unsupervised Reverse Dictionary","date":"2024-12-09","arxiv_id":"2412.06654","repositories_listed":1,"syntology":null},{"url":"/paper/incremental-sentence-processing-mechanisms-in","slug":"incremental-sentence-processing-mechanisms-in","title":"Incremental Sentence Processing Mechanisms in Autoregressive Transformer Language Models","date":"2024-12-06","arxiv_id":"2412.05353","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-consistency-based-uncertainty","slug":"semantic-consistency-based-uncertainty","title":"Semantic Consistency-Based Uncertainty Quantification for Factuality in Radiology Report Generation","date":"2024-12-05","arxiv_id":"2412.04606","repositories_listed":1,"syntology":null},{"url":"/paper/luxembedder-a-cross-lingual-approach-to","slug":"luxembedder-a-cross-lingual-approach-to","title":"LuxEmbedder: A Cross-Lingual Approach to Enhanced Luxembourgish Sentence Embeddings","date":"2024-12-04","arxiv_id":"2412.03331","repositories_listed":1,"syntology":null},{"url":"/paper/robust-multi-bit-text-watermark-with-llm","slug":"robust-multi-bit-text-watermark-with-llm","title":"Robust Multi-bit Text Watermark with LLM-based Paraphrasers","date":"2024-12-04","arxiv_id":"2412.03123","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":3,"n_no_contract":1,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 3 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/robust-multi-bit-text-watermark-with-llm#ran","syntology_url":"https://syntology.ai/paper/2412.03123","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.03123"}},"official":{"repos":["xiaojunxu/multi-bit-text-watermark"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/scaling-inference-time-search-with-vision","slug":"scaling-inference-time-search-with-vision","title":"Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension","date":"2024-12-04","arxiv_id":"2412.03704","repositories_listed":1,"syntology":null},{"url":"/paper/sitse-sinhala-text-simplification-dataset-and","slug":"sitse-sinhala-text-simplification-dataset-and","title":"SiTSE: Sinhala Text Simplification Dataset and Evaluation","date":"2024-12-02","arxiv_id":"2412.01293","repositories_listed":1,"syntology":null},{"url":"/paper/nushurescue-revitalization-of-the-endangered","slug":"nushurescue-revitalization-of-the-endangered","title":"NushuRescue: Revitalization of the Endangered Nushu Language with AI","date":"2024-11-29","arxiv_id":"2412.00218","repositories_listed":1,"syntology":null},{"url":"/paper/pralekha-an-indic-document-alignment","slug":"pralekha-an-indic-document-alignment","title":"Pralekha: An Indic Document Alignment Evaluation Benchmark","date":"2024-11-28","arxiv_id":"2411.19096","repositories_listed":1,"syntology":null},{"url":"/paper/cyber-attack-technique-classification-using","slug":"cyber-attack-technique-classification-using","title":"Cyber-Attack Technique Classification Using Two-Stage Trained Large Language Models","date":"2024-11-27","arxiv_id":"2411.18755","repositories_listed":1,"syntology":null},{"url":"/paper/a-novel-word-pair-based-gaussian-sentence","slug":"a-novel-word-pair-based-gaussian-sentence","title":"A Novel Word Pair-based Gaussian Sentence Similarity Algorithm For Bengali Extractive Text Summarization","date":"2024-11-26","arxiv_id":"2411.17181","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/azsld-azerbaijani-sign-language-dataset-for","slug":"azsld-azerbaijani-sign-language-dataset-for","title":"AzSLD: Azerbaijani Sign Language Dataset for Fingerspelling, Word, and Sentence Translation with Baseline Software","date":"2024-11-19","arxiv_id":"2411.12865","repositories_listed":1,"syntology":null},{"url":"/paper/nmt-obfuscator-attack-ignore-a-sentence-in","slug":"nmt-obfuscator-attack-ignore-a-sentence-in","title":"NMT-Obfuscator Attack: Ignore a sentence in translation with only one word","date":"2024-11-19","arxiv_id":"2411.12473","repositories_listed":1,"syntology":null},{"url":"/paper/counterfactual-generation-from-language","slug":"counterfactual-generation-from-language","title":"Gumbel Counterfactual Generation From Language Models","date":"2024-11-11","arxiv_id":"2411.07180","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/counterfactual-generation-from-language#ran","syntology_url":"https://syntology.ai/paper/2411.07180","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.07180"}},"official":{"repos":["shauli-ravfogel/lm-counterfactuals"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/using-language-models-to-disambiguate-lexical","slug":"using-language-models-to-disambiguate-lexical","title":"Using Language Models to Disambiguate Lexical Choices in Translation","date":"2024-11-08","arxiv_id":"2411.05781","repositories_listed":1,"syntology":null},{"url":"/paper/impscore-a-learnable-metric-for-quantifying","slug":"impscore-a-learnable-metric-for-quantifying","title":"ImpScore: A Learnable Metric For Quantifying The Implicitness Level of Language","date":"2024-11-07","arxiv_id":"2411.05172","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/impscore-a-learnable-metric-for-quantifying#ran","syntology_url":"https://syntology.ai/paper/2411.05172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.05172"}},"official":{"repos":["audreycs/impscore"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-creative-short-story-generation-in","slug":"evaluating-creative-short-story-generation-in","title":"Evaluating Creative Short Story Generation in Humans and Large Language Models","date":"2024-11-04","arxiv_id":"2411.02316","repositories_listed":1,"syntology":null},{"url":"/paper/moce-adaptive-mixture-of-contextualization","slug":"moce-adaptive-mixture-of-contextualization","title":"MoCE: Adaptive Mixture of Contextualization Experts for Byte-based Neural Machine Translation","date":"2024-11-03","arxiv_id":"2411.01474","repositories_listed":1,"syntology":null},{"url":"/paper/cmdcaliper-a-semantic-aware-command-line","slug":"cmdcaliper-a-semantic-aware-command-line","title":"CmdCaliper: A Semantic-Aware Command-Line Embedding Model and Dataset for Security Research","date":"2024-11-02","arxiv_id":"2411.01176","repositories_listed":1,"syntology":null},{"url":"/paper/phrase-decoupling-cross-modal-hierarchical","slug":"phrase-decoupling-cross-modal-hierarchical","title":"Phrase Decoupling Cross-Modal Hierarchical Matching and Progressive Position Correction for Visual Grounding","date":"2024-10-31","arxiv_id":"2410.23570","repositories_listed":1,"syntology":null},{"url":"/paper/vpo-leveraging-the-number-of-votes-in","slug":"vpo-leveraging-the-number-of-votes-in","title":"VPO: Leveraging the Number of Votes in Preference Optimization","date":"2024-10-30","arxiv_id":"2410.22891","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/vpo-leveraging-the-number-of-votes-in#ran","syntology_url":"https://syntology.ai/paper/2410.22891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.22891"}},"official":{"repos":["ku-dmlab/vpo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/instruction-tuned-llms-succeed-in-document","slug":"instruction-tuned-llms-succeed-in-document","title":"Fine-Grained and Multi-Dimensional Metrics for Document-Level Machine Translation","date":"2024-10-28","arxiv_id":"2410.20941","repositories_listed":1,"syntology":null},{"url":"/paper/dialog2flow-pre-training-soft-contrastive","slug":"dialog2flow-pre-training-soft-contrastive","title":"Dialog2Flow: Pre-training Soft-Contrastive Action-Driven Sentence Embeddings for Automatic Dialog Flow Extraction","date":"2024-10-24","arxiv_id":"2410.18481","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dialog2flow-pre-training-soft-contrastive#ran","syntology_url":"https://syntology.ai/paper/2410.18481","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.18481"}},"official":{"repos":["idiap/dialog2flow"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/science-out-of-its-ivory-tower-improving","slug":"science-out-of-its-ivory-tower-improving","title":"Science Out of Its Ivory Tower: Improving Accessibility with Reinforcement Learning","date":"2024-10-22","arxiv_id":"2410.17088","repositories_listed":1,"syntology":null},{"url":"/paper/autotrain-no-code-training-for-state-of-the","slug":"autotrain-no-code-training-for-state-of-the","title":"AutoTrain: No-code training for state-of-the-art models","date":"2024-10-21","arxiv_id":"2410.15735","repositories_listed":1,"syntology":null},{"url":"/paper/katzbot-revolutionizing-academic-chatbot-for","slug":"katzbot-revolutionizing-academic-chatbot-for","title":"KatzBot: Revolutionizing Academic Chatbot for Enhanced Communication","date":"2024-10-21","arxiv_id":"2410.16385","repositories_listed":1,"syntology":null},{"url":"/paper/geneol-harnessing-the-generative-power-of","slug":"geneol-harnessing-the-generative-power-of","title":"GenEOL: Harnessing the Generative Power of LLMs for Training-Free Sentence Embeddings","date":"2024-10-18","arxiv_id":"2410.14635","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"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) · 2 unverified","sample_list":"/paper/geneol-harnessing-the-generative-power-of#ran","syntology_url":"https://syntology.ai/paper/2410.14635","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14635"}},"official":{"repos":["raghavlite/GenEOL"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/unveiling-large-language-models-generated","slug":"unveiling-large-language-models-generated","title":"Unveiling Large Language Models Generated Texts: A Multi-Level Fine-Grained Detection Framework","date":"2024-10-18","arxiv_id":"2410.14231","repositories_listed":1,"syntology":null},{"url":"/paper/a-new-approach-for-fine-tuning-sentence","slug":"a-new-approach-for-fine-tuning-sentence","title":"A new approach for fine-tuning sentence transformers for intent classification and out-of-scope detection tasks","date":"2024-10-17","arxiv_id":"2410.13649","repositories_listed":1,"syntology":null},{"url":"/paper/less-label-efficient-and-single-stage","slug":"less-label-efficient-and-single-stage","title":"LESS: Label-Efficient and Single-Stage Referring 3D Segmentation","date":"2024-10-17","arxiv_id":"2410.13294","repositories_listed":1,"syntology":null},{"url":"/paper/meta-diffub-a-contextualized-sequence-to","slug":"meta-diffub-a-contextualized-sequence-to","title":"Meta-DiffuB: A Contextualized Sequence-to-Sequence Text Diffusion Model with Meta-Exploration","date":"2024-10-17","arxiv_id":"2410.13201","repositories_listed":1,"syntology":null},{"url":"/paper/kblam-knowledge-base-augmented-language-model","slug":"kblam-knowledge-base-augmented-language-model","title":"KBLaM: Knowledge Base augmented Language Model","date":"2024-10-14","arxiv_id":"2410.10450","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/kblam-knowledge-base-augmented-language-model#ran","syntology_url":"https://syntology.ai/paper/2410.10450","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10450"}},"official":{"repos":["microsoft/KBLaM"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/integrating-supertag-features-into-neural","slug":"integrating-supertag-features-into-neural","title":"Integrating Supertag Features into Neural Discontinuous Constituent Parsing","date":"2024-10-11","arxiv_id":"2410.08766","repositories_listed":1,"syntology":null},{"url":"/paper/a-closer-look-at-machine-unlearning-for-large","slug":"a-closer-look-at-machine-unlearning-for-large","title":"A Closer Look at Machine Unlearning for Large Language Models","date":"2024-10-10","arxiv_id":"2410.08109","repositories_listed":1,"syntology":{"n":17,"n_ran":12,"n_constructed":0,"n_ran_checked":7,"n_instrument":5,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":17,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/a-closer-look-at-machine-unlearning-for-large#ran","syntology_url":"https://syntology.ai/paper/2410.08109","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08109"}},"official":{"repos":["sail-sg/closer-look-llm-unlearning"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/delta-an-online-document-level-translation","slug":"delta-an-online-document-level-translation","title":"DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memory","date":"2024-10-10","arxiv_id":"2410.08143","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/delta-an-online-document-level-translation#ran","syntology_url":"https://syntology.ai/paper/2410.08143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08143"}},"official":{"repos":["yutongwang1216/docmtagent"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/melo-an-evaluation-benchmark-for-multilingual","slug":"melo-an-evaluation-benchmark-for-multilingual","title":"MELO: An Evaluation Benchmark for Multilingual Entity Linking of Occupations","date":"2024-10-10","arxiv_id":"2410.08319","repositories_listed":1,"syntology":null},{"url":"/paper/compositional-entailment-learning-for","slug":"compositional-entailment-learning-for","title":"Compositional Entailment Learning for Hyperbolic Vision-Language Models","date":"2024-10-09","arxiv_id":"2410.06912","repositories_listed":1,"syntology":{"n":13,"n_ran":7,"n_constructed":2,"n_ran_checked":2,"n_instrument":5,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":13,"phrase":"7 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/compositional-entailment-learning-for#ran","syntology_url":"https://syntology.ai/paper/2410.06912","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.06912"}},"official":{"repos":["PalAvik/hycoclip"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/eta-evaluating-then-aligning-safety-of-vision","slug":"eta-evaluating-then-aligning-safety-of-vision","title":"ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time","date":"2024-10-09","arxiv_id":"2410.06625","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":11,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/eta-evaluating-then-aligning-safety-of-vision#ran","syntology_url":"https://syntology.ai/paper/2410.06625","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.06625"}},"official":{"repos":["dripnowhy/eta"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-few-shot-learning-for-multi-label","slug":"efficient-few-shot-learning-for-multi-label","title":"Efficient Few-shot Learning for Multi-label Classification of Scientific Documents with Many Classes","date":"2024-10-08","arxiv_id":"2410.05770","repositories_listed":1,"syntology":null},{"url":"/paper/the-mystery-of-compositional-generalization","slug":"the-mystery-of-compositional-generalization","title":"The Mystery of Compositional Generalization in Graph-based Generative Commonsense Reasoning","date":"2024-10-08","arxiv_id":"2410.06272","repositories_listed":1,"syntology":null},{"url":"/paper/neural-machine-translation-system-for-lezgian","slug":"neural-machine-translation-system-for-lezgian","title":"Neural machine translation system for Lezgian, Russian and Azerbaijani languages","date":"2024-10-07","arxiv_id":"2410.05472","repositories_listed":1,"syntology":null},{"url":"/paper/a-simple-yet-effective-training-free-prompt","slug":"a-simple-yet-effective-training-free-prompt","title":"A Simple yet Effective Training-free Prompt-free Approach to Chinese Spelling Correction Based on Large Language Models","date":"2024-10-05","arxiv_id":"2410.04027","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"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) · 3 unverified","sample_list":"/paper/a-simple-yet-effective-training-free-prompt#ran","syntology_url":"https://syntology.ai/paper/2410.04027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04027"}},"official":{"repos":["Jacob-Zhou/simple-csc"],"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/faithcamera-construction-of-a-faithful","slug":"faithcamera-construction-of-a-faithful","title":"FaithCAMERA: Construction of a Faithful Dataset for Ad Text Generation","date":"2024-10-04","arxiv_id":"2410.03839","repositories_listed":1,"syntology":null},{"url":"/paper/generating-bilingual-example-sentences-with","slug":"generating-bilingual-example-sentences-with","title":"Generating bilingual example sentences with large language models as lexicography assistants","date":"2024-10-04","arxiv_id":"2410.03182","repositories_listed":1,"syntology":null},{"url":"/paper/grounded-videollm-sharpening-fine-grained","slug":"grounded-videollm-sharpening-fine-grained","title":"Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models","date":"2024-10-04","arxiv_id":"2410.03290","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/grounded-videollm-sharpening-fine-grained#ran","syntology_url":"https://syntology.ai/paper/2410.03290","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03290"}},"official":{"repos":["whb139426/grounded-video-llm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/corpipe-at-crac-2024-predicting-zero-mentions","slug":"corpipe-at-crac-2024-predicting-zero-mentions","title":"CorPipe at CRAC 2024: Predicting Zero Mentions from Raw Text","date":"2024-10-03","arxiv_id":"2410.02756","repositories_listed":1,"syntology":null},{"url":"/paper/crispo-multi-aspect-critique-suggestion","slug":"crispo-multi-aspect-critique-suggestion","title":"CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text Generation","date":"2024-10-03","arxiv_id":"2410.02748","repositories_listed":1,"syntology":null},{"url":"/paper/improving-unsupervised-constituency-parsing","slug":"improving-unsupervised-constituency-parsing","title":"Improving Unsupervised Constituency Parsing via Maximizing Semantic Information","date":"2024-10-03","arxiv_id":"2410.02558","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/improving-unsupervised-constituency-parsing#ran","syntology_url":"https://syntology.ai/paper/2410.02558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02558"}},"official":{"repos":["junjiechen-chris/improving-unsupervised-constituency-parsing-via-maximizing-semantic-information"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/make-compound-sentences-simple-to-analyze","slug":"make-compound-sentences-simple-to-analyze","title":"Make Compound Sentences Simple to Analyze: Learning to Split Sentences for Aspect-based Sentiment Analysis","date":"2024-10-03","arxiv_id":"2410.02297","repositories_listed":1,"syntology":null},{"url":"/paper/salient-information-prompting-to-steer","slug":"salient-information-prompting-to-steer","title":"Salient Information Prompting to Steer Content in Prompt-based Abstractive Summarization","date":"2024-10-03","arxiv_id":"2410.02741","repositories_listed":1,"syntology":null},{"url":"/paper/dlp-lora-efficient-task-specific-lora-fusion","slug":"dlp-lora-efficient-task-specific-lora-fusion","title":"DLP-LoRA: Efficient Task-Specific LoRA Fusion with a Dynamic, Lightweight Plugin for Large Language Models","date":"2024-10-02","arxiv_id":"2410.01497","repositories_listed":1,"syntology":null},{"url":"/paper/explain-like-i-m-five-using-llms-to-improve","slug":"explain-like-i-m-five-using-llms-to-improve","title":"Explain Like I'm Five: Using LLMs to Improve PDE Surrogate Models with Text","date":"2024-10-02","arxiv_id":"2410.01137","repositories_listed":1,"syntology":null},{"url":"/paper/factalign-long-form-factuality-alignment-of","slug":"factalign-long-form-factuality-alignment-of","title":"FactAlign: Long-form Factuality Alignment of Large Language Models","date":"2024-10-02","arxiv_id":"2410.01691","repositories_listed":1,"syntology":null},{"url":"/paper/fastlexrank-efficient-lexical-ranking-for","slug":"fastlexrank-efficient-lexical-ranking-for","title":"FastLexRank: Efficient Lexical Ranking for Structuring Social Media Posts","date":"2024-10-02","arxiv_id":"2410.01183","repositories_listed":1,"syntology":null},{"url":"/paper/risingballer-a-player-is-a-token-a-match-is-a","slug":"risingballer-a-player-is-a-token-a-match-is-a","title":"RisingBALLER: A player is a token, a match is a sentence, A path towards a foundational model for football players data analytics","date":"2024-10-01","arxiv_id":"2410.00943","repositories_listed":1,"syntology":null},{"url":"/paper/classification-of-radiological-text-in-small","slug":"classification-of-radiological-text-in-small","title":"Classification of Radiological Text in Small and Imbalanced Datasets in a Non-English Language","date":"2024-09-30","arxiv_id":"2409.20147","repositories_listed":1,"syntology":null},{"url":"/paper/helpd-mitigating-hallucination-of-lvlms-by","slug":"helpd-mitigating-hallucination-of-lvlms-by","title":"HELPD: Mitigating Hallucination of LVLMs by Hierarchical Feedback Learning with Vision-enhanced Penalty Decoding","date":"2024-09-30","arxiv_id":"2409.20429","repositories_listed":1,"syntology":null},{"url":"/paper/dimb-re-mining-the-scientific-literature-for","slug":"dimb-re-mining-the-scientific-literature-for","title":"DiMB-RE: Mining the Scientific Literature for Diet-Microbiome Associations","date":"2024-09-29","arxiv_id":"2409.19581","repositories_listed":1,"syntology":null},{"url":"/paper/edit-constrained-decoding-for-sentence","slug":"edit-constrained-decoding-for-sentence","title":"Edit-Constrained Decoding for Sentence Simplification","date":"2024-09-28","arxiv_id":"2409.19247","repositories_listed":1,"syntology":null},{"url":"/paper/multilingual-evaluation-of-long-context","slug":"multilingual-evaluation-of-long-context","title":"Evaluating Multilingual Long-Context Models for Retrieval and Reasoning","date":"2024-09-26","arxiv_id":"2409.18006","repositories_listed":1,"syntology":null},{"url":"/paper/how-transliterations-improve-crosslingual","slug":"how-transliterations-improve-crosslingual","title":"How Transliterations Improve Crosslingual Alignment","date":"2024-09-25","arxiv_id":"2409.17326","repositories_listed":1,"syntology":null},{"url":"/paper/ptq4ris-post-training-quantization-for","slug":"ptq4ris-post-training-quantization-for","title":"PTQ4RIS: Post-Training Quantization for Referring Image Segmentation","date":"2024-09-25","arxiv_id":"2409.17020","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-estimated-transferability-over","slug":"leveraging-estimated-transferability-over","title":"Leveraging Estimated Transferability Over Human Intuition for Model Selection in Text Ranking","date":"2024-09-24","arxiv_id":"2409.16198","repositories_listed":1,"syntology":null},{"url":"/paper/mitigating-semantic-leakage-in-cross-lingual","slug":"mitigating-semantic-leakage-in-cross-lingual","title":"Mitigating Semantic Leakage in Cross-lingual Embeddings via Orthogonality Constraint","date":"2024-09-24","arxiv_id":"2409.15664","repositories_listed":1,"syntology":null},{"url":"/paper/aste-transformer-modelling-dependencies-in","slug":"aste-transformer-modelling-dependencies-in","title":"ASTE Transformer Modelling Dependencies in Aspect-Sentiment Triplet Extraction","date":"2024-09-23","arxiv_id":"2409.15202","repositories_listed":1,"syntology":null},{"url":"/paper/mexma-token-level-objectives-improve-sentence","slug":"mexma-token-level-objectives-improve-sentence","title":"MEXMA: Token-level objectives improve sentence representations","date":"2024-09-19","arxiv_id":"2409.12737","repositories_listed":1,"syntology":null},{"url":"/paper/beeformer-bridging-the-gap-between-semantic","slug":"beeformer-bridging-the-gap-between-semantic","title":"beeFormer: Bridging the Gap Between Semantic and Interaction Similarity in Recommender Systems","date":"2024-09-16","arxiv_id":"2409.10309","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-italian-sentence-embeddings","slug":"exploring-italian-sentence-embeddings","title":"Exploring Italian sentence embeddings properties through multi-tasking","date":"2024-09-10","arxiv_id":"2409.06622","repositories_listed":1,"syntology":null},{"url":"/paper/longcite-enabling-llms-to-generate-fine","slug":"longcite-enabling-llms-to-generate-fine","title":"LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA","date":"2024-09-04","arxiv_id":"2409.02897","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/longcite-enabling-llms-to-generate-fine#ran","syntology_url":"https://syntology.ai/paper/2409.02897","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.02897"}},"official":{"repos":["THUDM/LongCite"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/2409-13695","slug":"2409-13695","title":"You Only Use Reactive Attention Slice For Long Context Retrieval","date":"2024-09-03","arxiv_id":"2409.13695","repositories_listed":1,"syntology":null},{"url":"/paper/agentre-an-agent-based-framework-for","slug":"agentre-an-agent-based-framework-for","title":"AgentRE: An Agent-Based Framework for Navigating Complex Information Landscapes in Relation Extraction","date":"2024-09-03","arxiv_id":"2409.01854","repositories_listed":1,"syntology":null},{"url":"/paper/less-is-more-concatenating-videos-for-sign","slug":"less-is-more-concatenating-videos-for-sign","title":"Less is more: concatenating videos for Sign Language Translation from a small set of signs","date":"2024-09-03","arxiv_id":"2409.01506","repositories_listed":1,"syntology":null},{"url":"/paper/personalized-lip-reading-adapting-to-your","slug":"personalized-lip-reading-adapting-to-your","title":"Personalized Lip Reading: Adapting to Your Unique Lip Movements with Vision and Language","date":"2024-09-02","arxiv_id":"2409.00986","repositories_listed":1,"syntology":null},{"url":"/paper/prompt-compression-with-context-aware","slug":"prompt-compression-with-context-aware","title":"Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inference","date":"2024-09-02","arxiv_id":"2409.01227","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/prompt-compression-with-context-aware#ran","syntology_url":"https://syntology.ai/paper/2409.01227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.01227"}},"official":{"repos":["workday/cpc"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/concse-unified-contrastive-learning-and","slug":"concse-unified-contrastive-learning-and","title":"ConCSE: Unified Contrastive Learning and Augmentation for Code-Switched Embeddings","date":"2024-08-28","arxiv_id":"2409.00120","repositories_listed":1,"syntology":null},{"url":"/paper/empowering-sign-language-communication","slug":"empowering-sign-language-communication","title":"Empowering Sign Language Communication: Integrating Sentiment and Semantics for Facial Expression Synthesis","date":"2024-08-27","arxiv_id":"2408.15159","repositories_listed":1,"syntology":null},{"url":"/paper/balancing-diversity-and-risk-in-llm-sampling","slug":"balancing-diversity-and-risk-in-llm-sampling","title":"Balancing Diversity and Risk in LLM Sampling: How to Select Your Method and Parameter for Open-Ended Text Generation","date":"2024-08-24","arxiv_id":"2408.13586","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/balancing-diversity-and-risk-in-llm-sampling#ran","syntology_url":"https://syntology.ai/paper/2408.13586","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.13586"}},"official":{"repos":["ZhouYuxuanYX/Benchmarking-and-Guiding-Adaptive-Sampling-Decoding-for-LLMs"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/beyond-dialogue-a-profile-dialogue-alignment","slug":"beyond-dialogue-a-profile-dialogue-alignment","title":"BEYOND DIALOGUE: A Profile-Dialogue Alignment Framework Towards General Role-Playing Language Model","date":"2024-08-20","arxiv_id":"2408.10903","repositories_listed":1,"syntology":null},{"url":"/paper/glimmer-incorporating-graph-and-lexical","slug":"glimmer-incorporating-graph-and-lexical","title":"GLIMMER: Incorporating Graph and Lexical Features in Unsupervised Multi-Document Summarization","date":"2024-08-19","arxiv_id":"2408.10115","repositories_listed":1,"syntology":null},{"url":"/paper/midas-multi-level-intent-domain-and-slot","slug":"midas-multi-level-intent-domain-and-slot","title":"MIDAS: Multi-level Intent, Domain, And Slot Knowledge Distillation for Multi-turn NLU","date":"2024-08-15","arxiv_id":"2408.08144","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-causal-reasoning-benchmark","slug":"multimodal-causal-reasoning-benchmark","title":"Multimodal Causal Reasoning Benchmark: Challenging Vision Large Language Models to Infer Causal Links Between Siamese Images","date":"2024-08-15","arxiv_id":"2408.08105","repositories_listed":1,"syntology":null},{"url":"/paper/sign-language-translation-with-sentence","slug":"sign-language-translation-with-sentence","title":"Sign Language Translation with Sentence Embedding Supervision","date":"2024-08-14","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/fastfid-improve-inference-efficiency-of-open","slug":"fastfid-improve-inference-efficiency-of-open","title":"FastFiD: Improve Inference Efficiency of Open Domain Question Answering via Sentence Selection","date":"2024-08-12","arxiv_id":"2408.06333","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/fastfid-improve-inference-efficiency-of-open#ran","syntology_url":"https://syntology.ai/paper/2408.06333","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.06333"}},"official":{"repos":["thunlp/fastfid"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/textit-re-cse-portable-reshaping-features-for","slug":"textit-re-cse-portable-reshaping-features-for","title":"reCSE: Portable Reshaping Features for Sentence Embedding in Self-supervised Contrastive Learning","date":"2024-08-09","arxiv_id":"2408.04975","repositories_listed":1,"syntology":null},{"url":"/paper/simplifying-translations-for-children","slug":"simplifying-translations-for-children","title":"Simplifying Translations for Children: Iterative Simplification Considering Age of Acquisition with LLMs","date":"2024-08-08","arxiv_id":"2408.04217","repositories_listed":1,"syntology":null},{"url":"/paper/artvlm-attribute-recognition-through-vision","slug":"artvlm-attribute-recognition-through-vision","title":"ArtVLM: Attribute Recognition Through Vision-Based Prefix Language Modeling","date":"2024-08-07","arxiv_id":"2408.04102","repositories_listed":1,"syntology":null},{"url":"/paper/2408-03099","slug":"2408-03099","title":"Topic Modeling with Fine-tuning LLMs and Bag of Sentences","date":"2024-08-06","arxiv_id":"2408.03099","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2408-03099#ran","syntology_url":"https://syntology.ai/paper/2408.03099","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.03099"}},"official":{"repos":["johntailor/ft-topic"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-03125","slug":"2408-03125","title":"COMMENTATOR: A Code-mixed Multilingual Text Annotation Framework","date":"2024-08-06","arxiv_id":"2408.03125","repositories_listed":1,"syntology":{"n":14,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":12,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 12 unverified","sample_list":"/paper/2408-03125#ran","syntology_url":"https://syntology.ai/paper/2408.03125","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.03125"}},"official":{"repos":["lingo-iitgn/commentator"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/2408-00397","slug":"2408-00397","title":"In-Context Example Selection via Similarity Search Improves Low-Resource Machine Translation","date":"2024-08-01","arxiv_id":"2408.00397","repositories_listed":1,"syntology":null},{"url":"/paper/2408-00655","slug":"2408-00655","title":"SentenceVAE: Enable Next-sentence Prediction for Large Language Models with Faster Speed, Higher Accuracy and Longer Context","date":"2024-08-01","arxiv_id":"2408.00655","repositories_listed":1,"syntology":null},{"url":"/paper/an-energy-based-model-for-word-level","slug":"an-energy-based-model-for-word-level","title":"An Energy-based Model for Word-level AutoCompletion in Computer-aided Translation","date":"2024-07-29","arxiv_id":"2407.20083","repositories_listed":1,"syntology":null},{"url":"/paper/can-editing-llms-inject-harm","slug":"can-editing-llms-inject-harm","title":"Can Editing LLMs Inject Harm?","date":"2024-07-29","arxiv_id":"2407.20224","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/can-editing-llms-inject-harm#ran","syntology_url":"https://syntology.ai/paper/2407.20224","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.20224"}},"official":null}},{"url":"/paper/granularity-is-crucial-when-applying","slug":"granularity-is-crucial-when-applying","title":"Granularity is crucial when applying differential privacy to text: An investigation for neural machine translation","date":"2024-07-26","arxiv_id":"2407.18789","repositories_listed":1,"syntology":null},{"url":"/paper/is-larger-always-better-evaluating-and","slug":"is-larger-always-better-evaluating-and","title":"ClinicRealm: Re-evaluating Large Language Models with Conventional Machine Learning for Non-Generative Clinical Prediction Tasks","date":"2024-07-26","arxiv_id":"2407.18525","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/is-larger-always-better-evaluating-and#ran","syntology_url":"https://syntology.ai/paper/2407.18525","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.18525"}},"official":{"repos":["yhzhu99/ehr-llm-benchmark"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-more-accurate-prediction-of-human","slug":"towards-more-accurate-prediction-of-human","title":"Towards More Accurate Prediction of Human Empathy and Emotion in Text and Multi-turn Conversations by Combining Advanced NLP, Transformers-based Networks, and Linguistic Methodologies","date":"2024-07-26","arxiv_id":"2407.18496","repositories_listed":1,"syntology":null},{"url":"/paper/tracking-linguistic-information-in","slug":"tracking-linguistic-information-in","title":"Tracking linguistic information in transformer-based sentence embeddings through targeted sparsification","date":"2024-07-25","arxiv_id":"2407.18119","repositories_listed":1,"syntology":null}],"record_sha256":"ae28b5802d1e4f36665202bbc53b35f48ef5287258989bfda90af446a07bc9b4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}