{"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/7","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":7,"pages_in_order":108,"rows_per_page":100,"rows":[601,700],"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/6","next":"/task/sentence/papers/8","papers":[{"url":"/paper/extraction-of-salient-sentences-from-labelled","slug":"extraction-of-salient-sentences-from-labelled","title":"Extraction of Salient Sentences from Labelled Documents","date":"2014-12-21","arxiv_id":"1412.6815","repositories_listed":2,"syntology":null},{"url":"/paper/deep-learning-for-answer-sentence-selection","slug":"deep-learning-for-answer-sentence-selection","title":"Deep Learning for Answer Sentence Selection","date":"2014-12-04","arxiv_id":"1412.1632","repositories_listed":2,"syntology":null},{"url":"/paper/bilbowa-fast-bilingual-distributed","slug":"bilbowa-fast-bilingual-distributed","title":"BilBOWA: Fast Bilingual Distributed Representations without Word Alignments","date":"2014-10-09","arxiv_id":"1410.2455","repositories_listed":2,"syntology":null},{"url":"/paper/keyphrase-extraction-for-n-best-reranking-in","slug":"keyphrase-extraction-for-n-best-reranking-in","title":"Keyphrase Extraction for N-best Reranking in Multi-Sentence Compression","date":"2013-06-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/mathematical-foundations-for-a-compositional","slug":"mathematical-foundations-for-a-compositional","title":"Mathematical Foundations for a Compositional Distributional Model of Meaning","date":"2010-03-23","arxiv_id":"1003.4394","repositories_listed":2,"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":0,"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/mathematical-foundations-for-a-compositional#ran","syntology_url":"https://syntology.ai/paper/1003.4394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1003.4394"}},"official":null}},{"url":"/paper/mitigating-object-hallucinations-via-sentence","slug":"mitigating-object-hallucinations-via-sentence","title":"Mitigating Object Hallucinations via Sentence-Level Early Intervention","date":"2025-07-16","arxiv_id":"2507.12455","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"7 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mitigating-object-hallucinations-via-sentence#ran","syntology_url":"https://syntology.ai/paper/2507.12455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.12455"}},"official":{"repos":["pspdada/SENTINEL"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ai-wizards-at-checkthat-2025-enhancing","slug":"ai-wizards-at-checkthat-2025-enhancing","title":"AI Wizards at CheckThat! 2025: Enhancing Transformer-Based Embeddings with Sentiment for Subjectivity Detection in News Articles","date":"2025-07-15","arxiv_id":"2507.11764","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-parameter-memory-temporary-lora","slug":"dynamic-parameter-memory-temporary-lora","title":"Dynamic Parameter Memory: Temporary LoRA-Enhanced LLM for Long-Sequence Emotion Recognition in Conversation","date":"2025-07-11","arxiv_id":"2507.09076","repositories_listed":1,"syntology":null},{"url":"/paper/finai-bert-a-transformer-based-model-for","slug":"finai-bert-a-transformer-based-model-for","title":"FinAI-BERT: A Transformer-Based Model for Sentence-Level Detection of AI Disclosures in Financial Reports","date":"2025-06-29","arxiv_id":"2507.01991","repositories_listed":1,"syntology":null},{"url":"/paper/thought-anchors-which-llm-reasoning-steps","slug":"thought-anchors-which-llm-reasoning-steps","title":"Thought Anchors: Which LLM Reasoning Steps Matter?","date":"2025-06-23","arxiv_id":"2506.19143","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/thought-anchors-which-llm-reasoning-steps#ran","syntology_url":"https://syntology.ai/paper/2506.19143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.19143"}},"official":null}},{"url":"/paper/2506-10558","slug":"2506-10558","title":"StepProof: Step-by-step verification of natural language mathematical proofs","date":"2025-06-12","arxiv_id":"2506.10558","repositories_listed":1,"syntology":null},{"url":"/paper/neuralnexus-at-bea-2025-shared-task-retrieval","slug":"neuralnexus-at-bea-2025-shared-task-retrieval","title":"NeuralNexus at BEA 2025 Shared Task: Retrieval-Augmented Prompting for Mistake Identification in AI Tutors","date":"2025-06-12","arxiv_id":"2506.10627","repositories_listed":1,"syntology":null},{"url":"/paper/a-mismatched-benchmark-for-scientific-natural","slug":"a-mismatched-benchmark-for-scientific-natural","title":"A MISMATCHED Benchmark for Scientific Natural Language Inference","date":"2025-06-05","arxiv_id":"2506.04603","repositories_listed":1,"syntology":null},{"url":"/paper/tokalign-efficient-vocabulary-adaptation-via","slug":"tokalign-efficient-vocabulary-adaptation-via","title":"TokAlign: Efficient Vocabulary Adaptation via Token Alignment","date":"2025-06-04","arxiv_id":"2506.03523","repositories_listed":1,"syntology":null},{"url":"/paper/the-reader-is-the-metric-how-textual-features","slug":"the-reader-is-the-metric-how-textual-features","title":"The Reader is the Metric: How Textual Features and Reader Profiles Explain Conflicting Evaluations of AI Creative Writing","date":"2025-06-03","arxiv_id":"2506.03310","repositories_listed":1,"syntology":null},{"url":"/paper/beavertalk-oregon-state-university-s-iwslt","slug":"beavertalk-oregon-state-university-s-iwslt","title":"BeaverTalk: Oregon State University's IWSLT 2025 Simultaneous Speech Translation System","date":"2025-05-29","arxiv_id":"2505.24016","repositories_listed":1,"syntology":null},{"url":"/paper/document-level-text-generation-with-minimum","slug":"document-level-text-generation-with-minimum","title":"Document-Level Text Generation with Minimum Bayes Risk Decoding using Optimal Transport","date":"2025-05-29","arxiv_id":"2505.23078","repositories_listed":1,"syntology":null},{"url":"/paper/sentinel-attention-probing-of-proxy-models","slug":"sentinel-attention-probing-of-proxy-models","title":"Sentinel: Attention Probing of Proxy Models for LLM Context Compression with an Understanding Perspective","date":"2025-05-29","arxiv_id":"2505.23277","repositories_listed":1,"syntology":null},{"url":"/paper/amplehate-amplifying-the-attention-for","slug":"amplehate-amplifying-the-attention-for","title":"AmpleHate: Amplifying the Attention for Versatile Implicit Hate Detection","date":"2025-05-26","arxiv_id":"2505.19528","repositories_listed":1,"syntology":null},{"url":"/paper/model-enumeration-of-two-variable-logic-with","slug":"model-enumeration-of-two-variable-logic-with","title":"Model Enumeration of Two-Variable Logic with Quadratic Delay Complexity","date":"2025-05-26","arxiv_id":"2505.19648","repositories_listed":1,"syntology":null},{"url":"/paper/mvp-multi-source-voice-pathology-detection","slug":"mvp-multi-source-voice-pathology-detection","title":"MVP: Multi-source Voice Pathology detection","date":"2025-05-26","arxiv_id":"2505.20050","repositories_listed":1,"syntology":null},{"url":"/paper/token-level-accept-or-reject-a-micro","slug":"token-level-accept-or-reject-a-micro","title":"Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models","date":"2025-05-26","arxiv_id":"2505.19743","repositories_listed":1,"syntology":null},{"url":"/paper/medscore-factuality-evaluation-of-free-form","slug":"medscore-factuality-evaluation-of-free-form","title":"MedScore: Factuality Evaluation of Free-Form Medical Answers","date":"2025-05-24","arxiv_id":"2505.18452","repositories_listed":1,"syntology":null},{"url":"/paper/a-japanese-language-model-and-three-new","slug":"a-japanese-language-model-and-three-new","title":"A Japanese Language Model and Three New Evaluation Benchmarks for Pharmaceutical NLP","date":"2025-05-22","arxiv_id":"2505.16661","repositories_listed":1,"syntology":null},{"url":"/paper/llms-are-not-scorers-rethinking-mt-evaluation","slug":"llms-are-not-scorers-rethinking-mt-evaluation","title":"LLMs Are Not Scorers: Rethinking MT Evaluation with Generation-Based Methods","date":"2025-05-22","arxiv_id":"2505.16129","repositories_listed":1,"syntology":null},{"url":"/paper/are-the-confidence-scores-of-reviewers","slug":"are-the-confidence-scores-of-reviewers","title":"Are the confidence scores of reviewers consistent with the review content? Evidence from top conference proceedings in AI","date":"2025-05-21","arxiv_id":"2505.15031","repositories_listed":1,"syntology":null},{"url":"/paper/a-personalized-conversational-benchmark","slug":"a-personalized-conversational-benchmark","title":"A Personalized Conversational Benchmark: Towards Simulating Personalized Conversations","date":"2025-05-20","arxiv_id":"2505.14106","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":6,"phrase":"5 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-personalized-conversational-benchmark#ran","syntology_url":"https://syntology.ai/paper/2505.14106","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.14106"}},"official":{"repos":["persona-bench/persona"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/adapting-pretrained-language-models-for-1","slug":"adapting-pretrained-language-models-for-1","title":"Adapting Pretrained Language Models for Citation Classification via Self-Supervised Contrastive Learning","date":"2025-05-20","arxiv_id":"2505.14471","repositories_listed":1,"syntology":null},{"url":"/paper/s2sbench-a-benchmark-for-quantifying","slug":"s2sbench-a-benchmark-for-quantifying","title":"S2SBench: A Benchmark for Quantifying Intelligence Degradation in Speech-to-Speech Large Language Models","date":"2025-05-20","arxiv_id":"2505.14438","repositories_listed":1,"syntology":null},{"url":"/paper/contrastive-prompting-enhances-sentence","slug":"contrastive-prompting-enhances-sentence","title":"Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering","date":"2025-05-19","arxiv_id":"2505.12831","repositories_listed":1,"syntology":null},{"url":"/paper/cross-lingual-representation-alignment","slug":"cross-lingual-representation-alignment","title":"Cross-Lingual Representation Alignment Through Contrastive Image-Caption Tuning","date":"2025-05-19","arxiv_id":"2505.13628","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/cross-lingual-representation-alignment#ran","syntology_url":"https://syntology.ai/paper/2505.13628","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.13628"}},"official":{"repos":["nkrasner/cl-clip-align"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/picturized-and-recited-with-dialects-a","slug":"picturized-and-recited-with-dialects-a","title":"Picturized and Recited with Dialects: A Multimodal Chinese Representation Framework for Sentiment Analysis of Classical Chinese Poetry","date":"2025-05-19","arxiv_id":"2505.13210","repositories_listed":1,"syntology":null},{"url":"/paper/to-bias-or-not-to-bias-detecting-bias-in-news","slug":"to-bias-or-not-to-bias-detecting-bias-in-news","title":"To Bias or Not to Bias: Detecting bias in News with bias-detector","date":"2025-05-19","arxiv_id":"2505.13010","repositories_listed":1,"syntology":null},{"url":"/paper/llm-based-evaluation-of-low-resource-machine","slug":"llm-based-evaluation-of-low-resource-machine","title":"LLM-Based Evaluation of Low-Resource Machine Translation: A Reference-less Dialect Guided Approach with a Refined Sylheti-English Benchmark","date":"2025-05-18","arxiv_id":"2505.12273","repositories_listed":1,"syntology":null},{"url":"/paper/words-that-unite-the-world-a-unified","slug":"words-that-unite-the-world-a-unified","title":"Words That Unite The World: A Unified Framework for Deciphering Central Bank Communications Globally","date":"2025-05-15","arxiv_id":"2505.17048","repositories_listed":1,"syntology":null},{"url":"/paper/chronocept-instilling-a-sense-of-time-in","slug":"chronocept-instilling-a-sense-of-time-in","title":"Chronocept: Instilling a Sense of Time in Machines","date":"2025-05-12","arxiv_id":"2505.07637","repositories_listed":1,"syntology":null},{"url":"/paper/ecolang-efficient-and-effective-agent","slug":"ecolang-efficient-and-effective-agent","title":"EcoLANG: Efficient and Effective Agent Communication Language Induction for Social Simulation","date":"2025-05-11","arxiv_id":"2505.06904","repositories_listed":1,"syntology":{"n":19,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/ecolang-efficient-and-effective-agent#ran","syntology_url":"https://syntology.ai/paper/2505.06904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.06904"}},"official":{"repos":["xymou/EcoLANG"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/sentence-embeddings-as-an-intermediate-target","slug":"sentence-embeddings-as-an-intermediate-target","title":"Sentence Embeddings as an intermediate target in end-to-end summarisation","date":"2025-05-06","arxiv_id":"2505.03481","repositories_listed":1,"syntology":null},{"url":"/paper/jtcse-joint-tensor-modulus-constraints-and","slug":"jtcse-joint-tensor-modulus-constraints-and","title":"JTCSE: Joint Tensor-Modulus Constraints and Cross-Attention for Unsupervised Contrastive Learning of Sentence Embeddings","date":"2025-05-05","arxiv_id":"2505.02366","repositories_listed":1,"syntology":null},{"url":"/paper/parameter-efficient-transformer-embeddings","slug":"parameter-efficient-transformer-embeddings","title":"Parameter-Efficient Transformer Embeddings","date":"2025-05-04","arxiv_id":"2505.02266","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-effectiveness-of-large-language-models-4","slug":"on-the-effectiveness-of-large-language-models-4","title":"On the effectiveness of Large Language Models in the mechanical design domain","date":"2025-05-02","arxiv_id":"2505.01559","repositories_listed":1,"syntology":null},{"url":"/paper/cse-sfp-enabling-unsupervised-sentence","slug":"cse-sfp-enabling-unsupervised-sentence","title":"CSE-SFP: Enabling Unsupervised Sentence Representation Learning via a Single Forward Pass","date":"2025-05-01","arxiv_id":"2505.00389","repositories_listed":1,"syntology":null},{"url":"/paper/20min-xd-a-comparable-corpus-of-swiss-news","slug":"20min-xd-a-comparable-corpus-of-swiss-news","title":"20min-XD: A Comparable Corpus of Swiss News Articles","date":"2025-04-30","arxiv_id":"2504.21677","repositories_listed":1,"syntology":null},{"url":"/paper/information-leakage-of-sentence-embeddings","slug":"information-leakage-of-sentence-embeddings","title":"Information Leakage of Sentence Embeddings via Generative Embedding Inversion Attacks","date":"2025-04-23","arxiv_id":"2504.16609","repositories_listed":1,"syntology":null},{"url":"/paper/fairtranslate-an-english-french-dataset-for","slug":"fairtranslate-an-english-french-dataset-for","title":"FairTranslate: An English-French Dataset for Gender Bias Evaluation in Machine Translation by Overcoming Gender Binarity","date":"2025-04-22","arxiv_id":"2504.15941","repositories_listed":1,"syntology":null},{"url":"/paper/dynamik-syntactically-driven-dynamic-font","slug":"dynamik-syntactically-driven-dynamic-font","title":"Dynamik: Syntactically-Driven Dynamic Font Sizing for Emphasis of Key Information","date":"2025-04-13","arxiv_id":"2504.09734","repositories_listed":1,"syntology":null},{"url":"/paper/llms-can-achieve-high-quality-simultaneous","slug":"llms-can-achieve-high-quality-simultaneous","title":"LLMs Can Achieve High-quality Simultaneous Machine Translation as Efficiently as Offline","date":"2025-04-13","arxiv_id":"2504.09570","repositories_listed":1,"syntology":null},{"url":"/paper/do-llms-understand-your-translations","slug":"do-llms-understand-your-translations","title":"Do LLMs Understand Your Translations? Evaluating Paragraph-level MT with Question Answering","date":"2025-04-10","arxiv_id":"2504.07583","repositories_listed":1,"syntology":null},{"url":"/paper/ruopinionne-2024-extraction-of-opinion-tuples","slug":"ruopinionne-2024-extraction-of-opinion-tuples","title":"RuOpinionNE-2024: Extraction of Opinion Tuples from Russian News Texts","date":"2025-04-09","arxiv_id":"2504.06947","repositories_listed":1,"syntology":null},{"url":"/paper/docia-an-online-document-level-context","slug":"docia-an-online-document-level-context","title":"DoCIA: An Online Document-Level Context Incorporation Agent for Speech Translation","date":"2025-04-07","arxiv_id":"2504.05122","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/goal-global-local-object-alignment-learning","slug":"goal-global-local-object-alignment-learning","title":"GOAL: Global-local Object Alignment Learning","date":"2025-03-22","arxiv_id":"2503.17782","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"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) · 1 unverified","sample_list":"/paper/goal-global-local-object-alignment-learning#ran","syntology_url":"https://syntology.ai/paper/2503.17782","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.17782"}},"official":{"repos":["perceptualai-lab/goal"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/ipcgrl-language-instructed-reinforcement","slug":"ipcgrl-language-instructed-reinforcement","title":"IPCGRL: Language-Instructed Reinforcement Learning for Procedural Level Generation","date":"2025-03-16","arxiv_id":"2503.12358","repositories_listed":1,"syntology":null},{"url":"/paper/an-expanded-massive-multilingual-dataset-for","slug":"an-expanded-massive-multilingual-dataset-for","title":"An Expanded Massive Multilingual Dataset for High-Performance Language Technologies","date":"2025-03-13","arxiv_id":"2503.10267","repositories_listed":1,"syntology":null},{"url":"/paper/domain-adaptation-for-japanese-sentence","slug":"domain-adaptation-for-japanese-sentence","title":"Domain Adaptation for Japanese Sentence Embeddings with Contrastive Learning based on Synthetic Sentence Generation","date":"2025-03-12","arxiv_id":"2503.09094","repositories_listed":1,"syntology":null},{"url":"/paper/language-models-fail-to-introspect-about","slug":"language-models-fail-to-introspect-about","title":"Language Models Fail to Introspect About Their Knowledge of Language","date":"2025-03-10","arxiv_id":"2503.07513","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/language-models-fail-to-introspect-about#ran","syntology_url":"https://syntology.ai/paper/2503.07513","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.07513"}},"official":{"repos":["siyuansong2004/language-introspection"],"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/dongbamie-a-multimodal-information-extraction","slug":"dongbamie-a-multimodal-information-extraction","title":"DongbaMIE: A Multimodal Information Extraction Dataset for Evaluating Semantic Understanding of Dongba Pictograms","date":"2025-03-05","arxiv_id":"2503.03644","repositories_listed":1,"syntology":null},{"url":"/paper/the-box-is-in-the-pen-evaluating-commonsense-1","slug":"the-box-is-in-the-pen-evaluating-commonsense-1","title":"The Box is in the Pen: Evaluating Commonsense Reasoning in Neural Machine Translation","date":"2025-03-05","arxiv_id":"2503.03308","repositories_listed":1,"syntology":null},{"url":"/paper/multilingual-relative-clause-attachment","slug":"multilingual-relative-clause-attachment","title":"Multilingual Relative Clause Attachment Ambiguity Resolution in Large Language Models","date":"2025-03-04","arxiv_id":"2503.02971","repositories_listed":1,"syntology":null},{"url":"/paper/off-clip-improving-normal-detection","slug":"off-clip-improving-normal-detection","title":"OFF-CLIP: Improving Normal Detection Confidence in Radiology CLIP with Simple Off-Diagonal Term Auto-Adjustment","date":"2025-03-03","arxiv_id":"2503.01794","repositories_listed":1,"syntology":null},{"url":"/paper/a-cooperative-multi-agent-framework-for-zero","slug":"a-cooperative-multi-agent-framework-for-zero","title":"A Cooperative Multi-Agent Framework for Zero-Shot Named Entity Recognition","date":"2025-02-25","arxiv_id":"2502.18702","repositories_listed":1,"syntology":null},{"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/longattn-selecting-long-context-training-data","slug":"longattn-selecting-long-context-training-data","title":"LongAttn: Selecting Long-context Training Data via Token-level Attention","date":"2025-02-24","arxiv_id":"2502.16860","repositories_listed":1,"syntology":null},{"url":"/paper/fanchuan-a-multilingual-and-graph-structured","slug":"fanchuan-a-multilingual-and-graph-structured","title":"FanChuan: A Multilingual and Graph-Structured Benchmark For Parody Detection and Analysis","date":"2025-02-23","arxiv_id":"2502.16503","repositories_listed":1,"syntology":null},{"url":"/paper/ordersum-semantic-sentence-ordering-for","slug":"ordersum-semantic-sentence-ordering-for","title":"OrderSum: Semantic Sentence Ordering for Extractive Summarization","date":"2025-02-22","arxiv_id":"2502.16180","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-rwkv-for-sentence-embeddings-layer","slug":"exploring-rwkv-for-sentence-embeddings-layer","title":"Exploring RWKV for Sentence Embeddings: Layer-wise Analysis and Baseline Comparison for Semantic Similarity","date":"2025-02-20","arxiv_id":"2502.14620","repositories_listed":1,"syntology":null},{"url":"/paper/refining-sentence-embedding-model-through","slug":"refining-sentence-embedding-model-through","title":"Refining Sentence Embedding Model through Ranking Sentences Generation with Large Language Models","date":"2025-02-19","arxiv_id":"2502.13656","repositories_listed":1,"syntology":null},{"url":"/paper/aligning-sentence-simplification-with-esl","slug":"aligning-sentence-simplification-with-esl","title":"Aligning Sentence Simplification with ESL Learner's Proficiency for Language Acquisition","date":"2025-02-17","arxiv_id":"2502.11457","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-evaluation-metrics-for-grammatical","slug":"rethinking-evaluation-metrics-for-grammatical","title":"Rethinking Evaluation Metrics for Grammatical Error Correction: Why Use a Different Evaluation Process than Human?","date":"2025-02-13","arxiv_id":"2502.09416","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/rethinking-evaluation-metrics-for-grammatical#ran","syntology_url":"https://syntology.ai/paper/2502.09416","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.09416"}},"official":{"repos":["gotutiyan/gec-metrics"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/selfcite-self-supervised-alignment-for","slug":"selfcite-self-supervised-alignment-for","title":"SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models","date":"2025-02-13","arxiv_id":"2502.09604","repositories_listed":1,"syntology":null},{"url":"/paper/a-large-scale-benchmark-for-vietnamese","slug":"a-large-scale-benchmark-for-vietnamese","title":"A Large-Scale Benchmark for Vietnamese Sentence Paraphrases","date":"2025-02-11","arxiv_id":"2502.07188","repositories_listed":1,"syntology":null},{"url":"/paper/aims-au-a-dataset-for-the-analysis-of-modern","slug":"aims-au-a-dataset-for-the-analysis-of-modern","title":"AIMS.au: A Dataset for the Analysis of Modern Slavery Countermeasures in Corporate Statements","date":"2025-02-10","arxiv_id":"2502.07022","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-annotation-augmentation-boosts","slug":"automatic-annotation-augmentation-boosts","title":"Automatic Annotation Augmentation Boosts Translation between Molecules and Natural Language","date":"2025-02-10","arxiv_id":"2502.06634","repositories_listed":1,"syntology":null},{"url":"/paper/multi-label-scandinavian-language","slug":"multi-label-scandinavian-language","title":"Multi-label Scandinavian Language Identification (SLIDE)","date":"2025-02-10","arxiv_id":"2502.06692","repositories_listed":1,"syntology":null},{"url":"/paper/smab-mab-based-word-sensitivity-estimation","slug":"smab-mab-based-word-sensitivity-estimation","title":"SMAB: MAB based word Sensitivity Estimation Framework and its Applications in Adversarial Text Generation","date":"2025-02-10","arxiv_id":"2502.07101","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/smab-mab-based-word-sensitivity-estimation#ran","syntology_url":"https://syntology.ai/paper/2502.07101","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.07101"}},"official":{"repos":["skp1999/SMAB"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/learning-to-substitute-words-with-model-based","slug":"learning-to-substitute-words-with-model-based","title":"Learning to Substitute Words with Model-based Score Ranking","date":"2025-02-09","arxiv_id":"2502.05933","repositories_listed":1,"syntology":null},{"url":"/paper/simmark-a-robust-sentence-level-similarity","slug":"simmark-a-robust-sentence-level-similarity","title":"SimMark: A Robust Sentence-Level Similarity-Based Watermarking Algorithm for Large Language Models","date":"2025-02-05","arxiv_id":"2502.02787","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":0,"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/simmark-a-robust-sentence-level-similarity#ran","syntology_url":"https://syntology.ai/paper/2502.02787","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.02787"}},"official":{"repos":["DabiriAghdam/SimMark"],"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/on-the-impact-of-noise-in-differentially","slug":"on-the-impact-of-noise-in-differentially","title":"On the Impact of Noise in Differentially Private Text Rewriting","date":"2025-01-31","arxiv_id":"2501.19022","repositories_listed":1,"syntology":null},{"url":"/paper/funzac-at-comedi-shared-task-modeling","slug":"funzac-at-comedi-shared-task-modeling","title":"Funzac at CoMeDi Shared Task: Modeling Annotator Disagreement from Word-In-Context Perspectives","date":"2025-01-24","arxiv_id":"2501.14617","repositories_listed":1,"syntology":null},{"url":"/paper/agentrec-agent-recommendation-using-sentence","slug":"agentrec-agent-recommendation-using-sentence","title":"AgentRec: Agent Recommendation Using Sentence Embeddings Aligned to Human Feedback","date":"2025-01-23","arxiv_id":"2501.13333","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-biomedical-relation-extraction-with-1","slug":"enhancing-biomedical-relation-extraction-with-1","title":"Enhancing Biomedical Relation Extraction with Directionality","date":"2025-01-23","arxiv_id":"2501.14079","repositories_listed":1,"syntology":null},{"url":"/paper/flanec-exploring-flan-t5-for-post-asr-error","slug":"flanec-exploring-flan-t5-for-post-asr-error","title":"FlanEC: Exploring Flan-T5 for Post-ASR Error Correction","date":"2025-01-22","arxiv_id":"2501.12979","repositories_listed":1,"syntology":null},{"url":"/paper/cross-entropy-attacks-to-language-models-via","slug":"cross-entropy-attacks-to-language-models-via","title":"Cross-Entropy Attacks to Language Models via Rare Event Simulation","date":"2025-01-21","arxiv_id":"2501.11852","repositories_listed":1,"syntology":null},{"url":"/paper/chartinsighter-an-approach-for-mitigating","slug":"chartinsighter-an-approach-for-mitigating","title":"ChartInsighter: An Approach for Mitigating Hallucination in Time-series Chart Summary Generation with A Benchmark Dataset","date":"2025-01-16","arxiv_id":"2501.09349","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-automated-interpretability-with","slug":"enhancing-automated-interpretability-with","title":"Enhancing Automated Interpretability with Output-Centric Feature Descriptions","date":"2025-01-14","arxiv_id":"2501.08319","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-retrieval-augmented-generation-a","slug":"enhancing-retrieval-augmented-generation-a","title":"Enhancing Retrieval-Augmented Generation: A Study of Best Practices","date":"2025-01-13","arxiv_id":"2501.07391","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/enhancing-retrieval-augmented-generation-a#ran","syntology_url":"https://syntology.ai/paper/2501.07391","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.07391"}},"official":{"repos":["ali-bahrainian/rag_best_practices"],"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/afridoc-mt-document-level-mt-corpus-for","slug":"afridoc-mt-document-level-mt-corpus-for","title":"AFRIDOC-MT: Document-level MT Corpus for African Languages","date":"2025-01-10","arxiv_id":"2501.06374","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-plagiarism-detection-in-marathi","slug":"enhancing-plagiarism-detection-in-marathi","title":"Enhancing Plagiarism Detection in Marathi with a Weighted Ensemble of TF-IDF and BERT Embeddings for Low-Resource Language Processing","date":"2025-01-09","arxiv_id":"2501.05260","repositories_listed":1,"syntology":null},{"url":"/paper/stream-aligner-efficient-sentence-level","slug":"stream-aligner-efficient-sentence-level","title":"Stream Aligner: Efficient Sentence-Level Alignment via Distribution Induction","date":"2025-01-09","arxiv_id":"2501.05336","repositories_listed":1,"syntology":null},{"url":"/paper/tougher-text-smarter-models-raising-the-bar","slug":"tougher-text-smarter-models-raising-the-bar","title":"Tougher Text, Smarter Models: Raising the Bar for Adversarial Defence Benchmarks","date":"2025-01-05","arxiv_id":"2501.02654","repositories_listed":1,"syntology":null},{"url":"/paper/cl-attack-textual-backdoor-attacks-via-cross","slug":"cl-attack-textual-backdoor-attacks-via-cross","title":"CL-Attack: Textual Backdoor Attacks via Cross-Lingual Triggers","date":"2024-12-26","arxiv_id":"2412.19037","repositories_listed":1,"syntology":null},{"url":"/paper/a-dual-perspective-metaphor-detection","slug":"a-dual-perspective-metaphor-detection","title":"A Dual-Perspective Metaphor Detection Framework Using Large Language Models","date":"2024-12-23","arxiv_id":"2412.17332","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/fine-tuning-whisper-on-low-resource-languages","slug":"fine-tuning-whisper-on-low-resource-languages","title":"Fine-tuning Whisper on Low-Resource Languages for Real-World Applications","date":"2024-12-20","arxiv_id":"2412.15726","repositories_listed":1,"syntology":null},{"url":"/paper/assessing-the-limitations-of-large-language","slug":"assessing-the-limitations-of-large-language","title":"Assessing the Limitations of Large Language Models in Clinical Fact Decomposition","date":"2024-12-17","arxiv_id":"2412.12422","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/exit-context-aware-extractive-compression-for","slug":"exit-context-aware-extractive-compression-for","title":"EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation","date":"2024-12-17","arxiv_id":"2412.12559","repositories_listed":1,"syntology":null},{"url":"/paper/improving-explainability-of-sentence-level","slug":"improving-explainability-of-sentence-level","title":"Improving Explainability of Sentence-level Metrics via Edit-level Attribution for Grammatical Error Correction","date":"2024-12-17","arxiv_id":"2412.13110","repositories_listed":1,"syntology":null},{"url":"/paper/an-incremental-clustering-baseline-for-event","slug":"an-incremental-clustering-baseline-for-event","title":"An Incremental Clustering Baseline for Event Detection on Twitter","date":"2024-12-16","arxiv_id":"2412.15257","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"]}}}],"record_sha256":"5b4ab811fae96c2ba6dfa66f1db152c7cb7036f2fa7bfa9d5e3553ffd43165e9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}