{"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/text-generation/papers/4","list_of":"/task/text-generation","task":"Text Generation","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":4,"pages_in_order":54,"rows_per_page":100,"rows":[301,400],"of":5335,"counts":{"archive_papers_tagged":5335,"with_a_code_link":2047,"where_syntology_ran_a_sample":610,"not_listed_spam_title":0,"listed":5335,"listed_where_code_ran":610,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":503,"every_run_a_failure_of_syntologys_instrument":107,"listed_with_a_run_with_no_instrument_failure":503,"listed_every_run_a_failure_of_syntologys_instrument":107,"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/text-generation","prev":"/task/text-generation/papers/3","next":"/task/text-generation/papers/5","papers":[{"url":"/paper/dgsan-discrete-generative-self-adversarial","slug":"dgsan-discrete-generative-self-adversarial","title":"DGSAN: Discrete Generative Self-Adversarial Network","date":"2019-08-24","arxiv_id":"1908.09127","repositories_listed":2,"syntology":null},{"url":"/paper/long-and-diverse-text-generation-with","slug":"long-and-diverse-text-generation-with","title":"Long and Diverse Text Generation with Planning-based Hierarchical Variational Model","date":"2019-08-19","arxiv_id":"1908.06605","repositories_listed":2,"syntology":null},{"url":"/paper/learning-to-select-track-and-generate-for","slug":"learning-to-select-track-and-generate-for","title":"Learning to Select, Track, and Generate for Data-to-Text","date":"2019-07-23","arxiv_id":"1907.09699","repositories_listed":2,"syntology":null},{"url":"/paper/er-ae-differentially-private-text-generation","slug":"er-ae-differentially-private-text-generation","title":"ER-AE: Differentially Private Text Generation for Authorship Anonymization","date":"2019-07-20","arxiv_id":"1907.08736","repositories_listed":2,"syntology":null},{"url":"/paper/writerforcing-generating-more-interesting","slug":"writerforcing-generating-more-interesting","title":"WriterForcing: Generating more interesting story endings","date":"2019-07-18","arxiv_id":"1907.08259","repositories_listed":2,"syntology":null},{"url":"/paper/data-to-text-generation-with-entity-modeling","slug":"data-to-text-generation-with-entity-modeling","title":"Data-to-text Generation with Entity Modeling","date":"2019-06-07","arxiv_id":"1906.03221","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/data-to-text-generation-with-entity-modeling#ran","syntology_url":"https://syntology.ai/paper/1906.03221","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.03221"}},"official":{"repos":["ratishsp/data2text-entity-py"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/generating-question-answer-hierarchies","slug":"generating-question-answer-hierarchies","title":"Generating Question-Answer Hierarchies","date":"2019-06-06","arxiv_id":"1906.02622","repositories_listed":2,"syntology":null},{"url":"/paper/reducing-gender-bias-in-word-level-language","slug":"reducing-gender-bias-in-word-level-language","title":"Reducing Gender Bias in Word-Level Language Models with a Gender-Equalizing Loss Function","date":"2019-05-30","arxiv_id":"1905.12801","repositories_listed":2,"syntology":null},{"url":"/paper/mu-forcing-training-variational-recurrent","slug":"mu-forcing-training-variational-recurrent","title":"mu-Forcing: Training Variational Recurrent Autoencoders for Text Generation","date":"2019-05-24","arxiv_id":"1905.10072","repositories_listed":2,"syntology":null},{"url":"/paper/paperrobot-incremental-draft-generation-of","slug":"paperrobot-incremental-draft-generation-of","title":"PaperRobot: Incremental Draft Generation of Scientific Ideas","date":"2019-05-20","arxiv_id":"1905.07870","repositories_listed":2,"syntology":null},{"url":"/paper/dual-supervised-learning-for-natural-language","slug":"dual-supervised-learning-for-natural-language","title":"Dual Supervised Learning for Natural Language Understanding and Generation","date":"2019-05-15","arxiv_id":"1905.06196","repositories_listed":2,"syntology":null},{"url":"/paper/few-shot-nlg-with-pre-trained-language-model","slug":"few-shot-nlg-with-pre-trained-language-model","title":"Few-Shot NLG with Pre-Trained Language Model","date":"2019-04-21","arxiv_id":"1904.09521","repositories_listed":2,"syntology":null},{"url":"/paper/pun-generation-with-surprise","slug":"pun-generation-with-surprise","title":"Pun Generation with Surprise","date":"2019-04-15","arxiv_id":"1904.06828","repositories_listed":2,"syntology":null},{"url":"/paper/unifying-human-and-statistical-evaluation-for","slug":"unifying-human-and-statistical-evaluation-for","title":"Unifying Human and Statistical Evaluation for Natural Language Generation","date":"2019-04-04","arxiv_id":"1904.02792","repositories_listed":2,"syntology":null},{"url":"/paper/pragmatically-informative-text-generation","slug":"pragmatically-informative-text-generation","title":"Pragmatically Informative Text Generation","date":"2019-04-02","arxiv_id":"1904.01301","repositories_listed":2,"syntology":null},{"url":"/paper/structural-neural-encoders-for-amr-to-text","slug":"structural-neural-encoders-for-amr-to-text","title":"Structural Neural Encoders for AMR-to-text Generation","date":"2019-03-27","arxiv_id":"1903.11410","repositories_listed":2,"syntology":null},{"url":"/paper/compare-mt-a-tool-for-holistic-comparison-of","slug":"compare-mt-a-tool-for-holistic-comparison-of","title":"compare-mt: A Tool for Holistic Comparison of Language Generation Systems","date":"2019-03-19","arxiv_id":"1903.07926","repositories_listed":2,"syntology":null},{"url":"/paper/what-makes-a-good-conversation-how","slug":"what-makes-a-good-conversation-how","title":"What makes a good conversation? How controllable attributes affect human judgments","date":"2019-02-22","arxiv_id":"1902.08654","repositories_listed":2,"syntology":null},{"url":"/paper/lagging-inference-networks-and-posterior","slug":"lagging-inference-networks-and-posterior","title":"Lagging Inference Networks and Posterior Collapse in Variational Autoencoders","date":"2019-01-16","arxiv_id":"1901.05534","repositories_listed":2,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/lagging-inference-networks-and-posterior#ran","syntology_url":"https://syntology.ai/paper/1901.05534","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.05534"}},"official":{"repos":["jxhe/vae-lagging-encoder"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/handling-rare-items-in-data-to-text","slug":"handling-rare-items-in-data-to-text","title":"Handling Rare Items in Data-to-Text Generation","date":"2018-11-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/the-natural-auditor-how-to-tell-if-someone","slug":"the-natural-auditor-how-to-tell-if-someone","title":"Auditing Data Provenance in Text-Generation Models","date":"2018-11-01","arxiv_id":"1811.00513","repositories_listed":2,"syntology":null},{"url":"/paper/deep-graph-convolutional-encoders-for","slug":"deep-graph-convolutional-encoders-for","title":"Deep Graph Convolutional Encoders for Structured Data to Text Generation","date":"2018-10-23","arxiv_id":"1810.09995","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deep-graph-convolutional-encoders-for#ran","syntology_url":"https://syntology.ai/paper/1810.09995","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.09995"}},"official":{"repos":["diegma/graph-2-text"],"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/data-to-text-generation-with-content","slug":"data-to-text-generation-with-content","title":"Data-to-Text Generation with Content Selection and Planning","date":"2018-09-03","arxiv_id":"1809.00582","repositories_listed":2,"syntology":null},{"url":"/paper/learning-neural-templates-for-text-generation","slug":"learning-neural-templates-for-text-generation","title":"Learning Neural Templates for Text Generation","date":"2018-08-30","arxiv_id":"1808.10122","repositories_listed":2,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 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; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/learning-neural-templates-for-text-generation#ran","syntology_url":"https://syntology.ai/paper/1808.10122","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.10122"}},"official":{"repos":["harvardnlp/neural-template-gen"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/paper-abstract-writing-through-editing","slug":"paper-abstract-writing-through-editing","title":"Paper Abstract Writing through Editing Mechanism","date":"2018-05-15","arxiv_id":"1805.06064","repositories_listed":2,"syntology":null},{"url":"/paper/zero-shot-dialog-generation-with-cross-domain","slug":"zero-shot-dialog-generation-with-cross-domain","title":"Zero-Shot Dialog Generation with Cross-Domain Latent Actions","date":"2018-05-13","arxiv_id":"1805.04803","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/zero-shot-dialog-generation-with-cross-domain#ran","syntology_url":"https://syntology.ai/paper/1805.04803","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.04803"}},"official":{"repos":["snakeztc/NeuralDialog-ZSDG","snakeztc/SimDial"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/unsupervised-discrete-sentence-representation","slug":"unsupervised-discrete-sentence-representation","title":"Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation","date":"2018-04-22","arxiv_id":"1804.08069","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unsupervised-discrete-sentence-representation#ran","syntology_url":"https://syntology.ai/paper/1804.08069","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.08069"}},"official":{"repos":["snakeztc/NeuralDialog-LAED"],"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":["listed","official"]}}},{"url":"/paper/sobolev-gan","slug":"sobolev-gan","title":"Sobolev GAN","date":"2017-11-14","arxiv_id":"1711.04894","repositories_listed":2,"syntology":null},{"url":"/paper/the-e2e-dataset-new-challenges-for-end-to-end","slug":"the-e2e-dataset-new-challenges-for-end-to-end","title":"The E2E Dataset: New Challenges For End-to-End Generation","date":"2017-06-28","arxiv_id":"1706.09254","repositories_listed":2,"syntology":null},{"url":"/paper/deep-reinforcement-learning-an-overview","slug":"deep-reinforcement-learning-an-overview","title":"Deep Reinforcement Learning: An Overview","date":"2017-01-25","arxiv_id":"1701.07274","repositories_listed":2,"syntology":null},{"url":"/paper/piecewise-latent-variables-for-neural","slug":"piecewise-latent-variables-for-neural","title":"Piecewise Latent Variables for Neural Variational Text Processing","date":"2016-12-01","arxiv_id":"1612.00377","repositories_listed":2,"syntology":null},{"url":"/paper/neural-text-generation-from-structured-data","slug":"neural-text-generation-from-structured-data","title":"Neural Text Generation from Structured Data with Application to the Biography Domain","date":"2016-03-24","arxiv_id":"1603.07771","repositories_listed":2,"syntology":null},{"url":"/paper/latent-predictor-networks-for-code-generation","slug":"latent-predictor-networks-for-code-generation","title":"Latent Predictor Networks for Code Generation","date":"2016-03-22","arxiv_id":"1603.06744","repositories_listed":2,"syntology":null},{"url":"/paper/semantically-conditioned-lstm-based-natural","slug":"semantically-conditioned-lstm-based-natural","title":"Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems","date":"2015-08-07","arxiv_id":"1508.01745","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":0,"n_honours":4,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 4 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/semantically-conditioned-lstm-based-natural#ran","syntology_url":"https://syntology.ai/paper/1508.01745","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1508.01745"}},"official":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/making-language-model-a-hierarchical","slug":"making-language-model-a-hierarchical","title":"Making Language Model a Hierarchical Classifier and Generator","date":"2025-07-17","arxiv_id":"2507.12930","repositories_listed":1,"syntology":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/hashed-watermark-as-a-filter-defeating","slug":"hashed-watermark-as-a-filter-defeating","title":"Hashed Watermark as a Filter: Defeating Forging and Overwriting Attacks in Weight-based Neural Network Watermarking","date":"2025-07-15","arxiv_id":"2507.11137","repositories_listed":1,"syntology":null},{"url":"/paper/seq-vs-seq-an-open-suite-of-paired-encoders","slug":"seq-vs-seq-an-open-suite-of-paired-encoders","title":"Seq vs Seq: An Open Suite of Paired Encoders and Decoders","date":"2025-07-15","arxiv_id":"2507.11412","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/seq-vs-seq-an-open-suite-of-paired-encoders#ran","syntology_url":"https://syntology.ai/paper/2507.11412","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.11412"}},"official":{"repos":["jhu-clsp/ettin-encoder-vs-decoder"],"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/the-devil-behind-the-mask-an-emergent-safety","slug":"the-devil-behind-the-mask-an-emergent-safety","title":"The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs","date":"2025-07-15","arxiv_id":"2507.11097","repositories_listed":1,"syntology":{"n":17,"n_ran":16,"n_constructed":0,"n_ran_checked":12,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":15,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/the-devil-behind-the-mask-an-emergent-safety#ran","syntology_url":"https://syntology.ai/paper/2507.11097","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.11097"}},"official":{"repos":["zichenwen1/dija"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/openfactscore-open-source-atomic-evaluation","slug":"openfactscore-open-source-atomic-evaluation","title":"OpenFActScore: Open-Source Atomic Evaluation of Factuality in Text Generation","date":"2025-07-08","arxiv_id":"2507.05965","repositories_listed":1,"syntology":null},{"url":"/paper/mitigating-hallucination-of-large-vision","slug":"mitigating-hallucination-of-large-vision","title":"Mitigating Hallucination of Large Vision-Language Models via Dynamic Logits Calibration","date":"2025-06-26","arxiv_id":"2506.21509","repositories_listed":1,"syntology":null},{"url":"/paper/spotting-out-of-character-behavior-atomic","slug":"spotting-out-of-character-behavior-atomic","title":"Spotting Out-of-Character Behavior: Atomic-Level Evaluation of Persona Fidelity in Open-Ended Generation","date":"2025-06-24","arxiv_id":"2506.19352","repositories_listed":1,"syntology":null},{"url":"/paper/longwriter-zero-mastering-ultra-long-text","slug":"longwriter-zero-mastering-ultra-long-text","title":"LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning","date":"2025-06-23","arxiv_id":"2506.18841","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":6,"n_instrument":6,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/longwriter-zero-mastering-ultra-long-text#ran","syntology_url":"https://syntology.ai/paper/2506.18841","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.18841"}},"official":null}},{"url":"/paper/omnigen2-exploration-to-advanced-multimodal","slug":"omnigen2-exploration-to-advanced-multimodal","title":"OmniGen2: Exploration to Advanced Multimodal Generation","date":"2025-06-23","arxiv_id":"2506.18871","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/omnigen2-exploration-to-advanced-multimodal#ran","syntology_url":"https://syntology.ai/paper/2506.18871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.18871"}},"official":{"repos":["vectorspacelab/omnigen2"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/generationprograms-fine-grained-attribution","slug":"generationprograms-fine-grained-attribution","title":"GenerationPrograms: Fine-grained Attribution with Executable Programs","date":"2025-06-17","arxiv_id":"2506.14580","repositories_listed":1,"syntology":null},{"url":"/paper/igd-token-decisiveness-modeling-via","slug":"igd-token-decisiveness-modeling-via","title":"IGD: Token Decisiveness Modeling via Information Gain in LLMs for Personalized Recommendation","date":"2025-06-16","arxiv_id":"2506.13229","repositories_listed":1,"syntology":null},{"url":"/paper/tagrouter-learning-route-to-llms-through-tags","slug":"tagrouter-learning-route-to-llms-through-tags","title":"TagRouter: Learning Route to LLMs through Tags for Open-Domain Text Generation Tasks","date":"2025-06-14","arxiv_id":"2506.12473","repositories_listed":1,"syntology":null},{"url":"/paper/2506-10467","slug":"2506-10467","title":"Specification and Evaluation of Multi-Agent LLM Systems -- Prototype and Cybersecurity Applications","date":"2025-06-12","arxiv_id":"2506.10467","repositories_listed":1,"syntology":null},{"url":"/paper/the-diffusion-duality","slug":"the-diffusion-duality","title":"The Diffusion Duality","date":"2025-06-12","arxiv_id":"2506.10892","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/the-diffusion-duality#ran","syntology_url":"https://syntology.ai/paper/2506.10892","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.10892"}},"official":{"repos":["s-sahoo/duo"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community"]}}},{"url":"/paper/omnidrca-parallel-speech-text-foundation","slug":"omnidrca-parallel-speech-text-foundation","title":"OmniDRCA: Parallel Speech-Text Foundation Model via Dual-Resolution Speech Representations and Contrastive Alignment","date":"2025-06-11","arxiv_id":"2506.09349","repositories_listed":1,"syntology":null},{"url":"/paper/revisit-what-you-see-disclose-language-prior","slug":"revisit-what-you-see-disclose-language-prior","title":"Revisit What You See: Disclose Language Prior in Vision Tokens for Efficient Guided Decoding of LVLMs","date":"2025-06-11","arxiv_id":"2506.09522","repositories_listed":1,"syntology":null},{"url":"/paper/diffuse-everything-multimodal-diffusion","slug":"diffuse-everything-multimodal-diffusion","title":"Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spaces","date":"2025-06-09","arxiv_id":"2506.07903","repositories_listed":1,"syntology":null},{"url":"/paper/eliciting-fine-tuned-transformer-capabilities","slug":"eliciting-fine-tuned-transformer-capabilities","title":"Eliciting Fine-Tuned Transformer Capabilities via Inference-Time Techniques","date":"2025-06-09","arxiv_id":"2506.08060","repositories_listed":1,"syntology":null},{"url":"/paper/heavywater-and-simplexwater-watermarking-low","slug":"heavywater-and-simplexwater-watermarking-low","title":"HeavyWater and SimplexWater: Watermarking Low-Entropy Text Distributions","date":"2025-06-06","arxiv_id":"2506.06409","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/heavywater-and-simplexwater-watermarking-low#ran","syntology_url":"https://syntology.ai/paper/2506.06409","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.06409"}},"official":{"repos":["dortsur/heavywater_simplexwater"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/time-to-talk-llm-agents-for-asynchronous","slug":"time-to-talk-llm-agents-for-asynchronous","title":"Time to Talk: LLM Agents for Asynchronous Group Communication in Mafia Games","date":"2025-06-05","arxiv_id":"2506.05309","repositories_listed":1,"syntology":null},{"url":"/paper/superwriter-reflection-driven-long-form","slug":"superwriter-reflection-driven-long-form","title":"SuperWriter: Reflection-Driven Long-Form Generation with Large Language Models","date":"2025-06-04","arxiv_id":"2506.04180","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/superwriter-reflection-driven-long-form#ran","syntology_url":"https://syntology.ai/paper/2506.04180","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.04180"}},"official":{"repos":["mozhu621/superwriter"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/watermarking-degrades-alignment-in-language","slug":"watermarking-degrades-alignment-in-language","title":"Watermarking Degrades Alignment in Language Models: Analysis and Mitigation","date":"2025-06-04","arxiv_id":"2506.04462","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/watermarking-degrades-alignment-in-language#ran","syntology_url":"https://syntology.ai/paper/2506.04462","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.04462"}},"official":{"repos":["dapurv5/alignmark"],"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/hypersteer-activation-steering-at-scale-with","slug":"hypersteer-activation-steering-at-scale-with","title":"HyperSteer: Activation Steering at Scale with Hypernetworks","date":"2025-06-03","arxiv_id":"2506.03292","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/probing-neural-topology-of-large-language","slug":"probing-neural-topology-of-large-language","title":"Probing Neural Topology of Large Language Models","date":"2025-06-01","arxiv_id":"2506.01042","repositories_listed":1,"syntology":null},{"url":"/paper/2506-00381","slug":"2506-00381","title":"Neuro2Semantic: A Transfer Learning Framework for Semantic Reconstruction of Continuous Language from Human Intracranial EEG","date":"2025-05-31","arxiv_id":"2506.00381","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-lora-merge-with-parameter-pruning","slug":"adaptive-lora-merge-with-parameter-pruning","title":"Adaptive LoRA Merge with Parameter Pruning for Low-Resource Generation","date":"2025-05-30","arxiv_id":"2505.24174","repositories_listed":1,"syntology":null},{"url":"/paper/multilingual-gloss-free-sign-language","slug":"multilingual-gloss-free-sign-language","title":"Multilingual Gloss-free Sign Language Translation: Towards Building a Sign Language Foundation Model","date":"2025-05-30","arxiv_id":"2505.24355","repositories_listed":1,"syntology":null},{"url":"/paper/discriminative-policy-optimization-for-token","slug":"discriminative-policy-optimization-for-token","title":"Discriminative Policy Optimization for Token-Level Reward Models","date":"2025-05-29","arxiv_id":"2505.23363","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"2 ran (of which 1 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) · 3 unverified","sample_list":"/paper/discriminative-policy-optimization-for-token#ran","syntology_url":"https://syntology.ai/paper/2505.23363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23363"}},"official":{"repos":["homzer/q-rm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"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/how-does-response-length-affect-long-form","slug":"how-does-response-length-affect-long-form","title":"How Does Response Length Affect Long-Form Factuality","date":"2025-05-29","arxiv_id":"2505.23295","repositories_listed":1,"syntology":null},{"url":"/paper/muddit-liberating-generation-beyond-text-to","slug":"muddit-liberating-generation-beyond-text-to","title":"Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model","date":"2025-05-29","arxiv_id":"2505.23606","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/muddit-liberating-generation-beyond-text-to#ran","syntology_url":"https://syntology.ai/paper/2505.23606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23606"}},"official":{"repos":["m-e-agi-lab/muddit"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-paraphrase-type-generation-the","slug":"enhancing-paraphrase-type-generation-the","title":"Enhancing Paraphrase Type Generation: The Impact of DPO and RLHF Evaluated with Human-Ranked Data","date":"2025-05-28","arxiv_id":"2506.02018","repositories_listed":1,"syntology":null},{"url":"/paper/makieval-a-multilingual-automatic-wikidata","slug":"makieval-a-multilingual-automatic-wikidata","title":"MAKIEval: A Multilingual Automatic WiKidata-based Framework for Cultural Awareness Evaluation for LLMs","date":"2025-05-27","arxiv_id":"2505.21693","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-classifier-free-guidance-via-dynamic","slug":"adaptive-classifier-free-guidance-via-dynamic","title":"Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Masking","date":"2025-05-26","arxiv_id":"2505.20199","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-text-based-protein-understanding","slug":"rethinking-text-based-protein-understanding","title":"Rethinking Text-based Protein Understanding: Retrieval or LLM?","date":"2025-05-26","arxiv_id":"2505.20354","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/rethinking-text-based-protein-understanding#ran","syntology_url":"https://syntology.ai/paper/2505.20354","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.20354"}},"official":{"repos":["IDEA-XL/RAPM"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/smoothie-smoothing-diffusion-on-token","slug":"smoothie-smoothing-diffusion-on-token","title":"Smoothie: Smoothing Diffusion on Token Embeddings for Text Generation","date":"2025-05-24","arxiv_id":"2505.18853","repositories_listed":1,"syntology":{"n":12,"n_ran":6,"n_constructed":2,"n_ran_checked":4,"n_instrument":2,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":12,"phrase":"6 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/smoothie-smoothing-diffusion-on-token#ran","syntology_url":"https://syntology.ai/paper/2505.18853","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.18853"}},"official":{"repos":["ashaba1in/smoothie"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/syn3dtxt-embedding-3d-cues-for-scene-text","slug":"syn3dtxt-embedding-3d-cues-for-scene-text","title":"Syn3DTxt: Embedding 3D Cues for Scene Text Generation","date":"2025-05-24","arxiv_id":"2505.18479","repositories_listed":1,"syntology":null},{"url":"/paper/writing-like-the-best-exemplar-based","slug":"writing-like-the-best-exemplar-based","title":"Writing Like the Best: Exemplar-Based Expository Text Generation","date":"2025-05-24","arxiv_id":"2505.18859","repositories_listed":1,"syntology":null},{"url":"/paper/appealcase-a-dataset-and-benchmark-for-civil","slug":"appealcase-a-dataset-and-benchmark-for-civil","title":"AppealCase: A Dataset and Benchmark for Civil Case Appeal Scenarios","date":"2025-05-22","arxiv_id":"2505.16514","repositories_listed":1,"syntology":null},{"url":"/paper/castillo-characterizing-response-length","slug":"castillo-characterizing-response-length","title":"CASTILLO: Characterizing Response Length Distributions of Large Language Models","date":"2025-05-22","arxiv_id":"2505.16881","repositories_listed":1,"syntology":null},{"url":"/paper/duffin-a-dual-level-fingerprinting-framework","slug":"duffin-a-dual-level-fingerprinting-framework","title":"DuFFin: A Dual-Level Fingerprinting Framework for LLMs IP Protection","date":"2025-05-22","arxiv_id":"2505.16530","repositories_listed":1,"syntology":null},{"url":"/paper/lifebench-evaluating-length-instruction","slug":"lifebench-evaluating-length-instruction","title":"LIFEBench: Evaluating Length Instruction Following in Large Language Models","date":"2025-05-22","arxiv_id":"2505.16234","repositories_listed":1,"syntology":null},{"url":"/paper/power-law-decay-loss-for-large-language-model","slug":"power-law-decay-loss-for-large-language-model","title":"Power-Law Decay Loss for Large Language Model Finetuning: Focusing on Information Sparsity to Enhance Generation Quality","date":"2025-05-22","arxiv_id":"2505.16900","repositories_listed":1,"syntology":null},{"url":"/paper/thinkrec-thinking-based-recommendation-via","slug":"thinkrec-thinking-based-recommendation-via","title":"ThinkRec: Thinking-based recommendation via LLM","date":"2025-05-21","arxiv_id":"2505.15091","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/addressing-the-challenges-of-planning","slug":"addressing-the-challenges-of-planning","title":"Addressing the Challenges of Planning Language Generation","date":"2025-05-20","arxiv_id":"2505.14763","repositories_listed":1,"syntology":null},{"url":"/paper/eeg-to-text-translation-a-model-for","slug":"eeg-to-text-translation-a-model-for","title":"EEG-to-Text Translation: A Model for Deciphering Human Brain Activity","date":"2025-05-20","arxiv_id":"2505.13936","repositories_listed":1,"syntology":null},{"url":"/paper/mug-eval-a-proxy-evaluation-framework-for","slug":"mug-eval-a-proxy-evaluation-framework-for","title":"MUG-Eval: A Proxy Evaluation Framework for Multilingual Generation Capabilities in Any Language","date":"2025-05-20","arxiv_id":"2505.14395","repositories_listed":1,"syntology":null},{"url":"/paper/process-vs-outcome-reward-which-is-better-for","slug":"process-vs-outcome-reward-which-is-better-for","title":"Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning","date":"2025-05-20","arxiv_id":"2505.14069","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/process-vs-outcome-reward-which-is-better-for#ran","syntology_url":"https://syntology.ai/paper/2505.14069","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.14069"}},"official":{"repos":["wlzhang2020/reasonrag"],"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/qa-prompting-improving-summarization-with","slug":"qa-prompting-improving-summarization-with","title":"QA-prompting: Improving Summarization with Large Language Models using Question-Answering","date":"2025-05-20","arxiv_id":"2505.14347","repositories_listed":1,"syntology":null},{"url":"/paper/u-sam-an-audio-language-model-for-unified","slug":"u-sam-an-audio-language-model-for-unified","title":"U-SAM: An audio language Model for Unified Speech, Audio, and Music Understanding","date":"2025-05-20","arxiv_id":"2505.13880","repositories_listed":1,"syntology":null},{"url":"/paper/know3-rag-a-knowledge-aware-rag-framework","slug":"know3-rag-a-knowledge-aware-rag-framework","title":"Know3-RAG: A Knowledge-aware RAG Framework with Adaptive Retrieval, Generation, and Filtering","date":"2025-05-19","arxiv_id":"2505.12662","repositories_listed":1,"syntology":null},{"url":"/paper/writevit-handwritten-text-generation-with","slug":"writevit-handwritten-text-generation-with","title":"WriteViT: Handwritten Text Generation with Vision Transformer","date":"2025-05-19","arxiv_id":"2505.13235","repositories_listed":1,"syntology":null},{"url":"/paper/fastcar-cache-attentive-replay-for-fast-auto","slug":"fastcar-cache-attentive-replay-for-fast-auto","title":"FastCar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edge","date":"2025-05-17","arxiv_id":"2505.14709","repositories_listed":1,"syntology":null},{"url":"/paper/2505-10852","slug":"2505-10852","title":"MatTools: Benchmarking Large Language Models for Materials Science Tools","date":"2025-05-16","arxiv_id":"2505.10852","repositories_listed":1,"syntology":null},{"url":"/paper/2505-11326","slug":"2505-11326","title":"Temporally-Grounded Language Generation: A Benchmark for Real-Time Vision-Language Models","date":"2025-05-16","arxiv_id":"2505.11326","repositories_listed":1,"syntology":null},{"url":"/paper/complexformer-disruptively-advancing","slug":"complexformer-disruptively-advancing","title":"ComplexFormer: Disruptively Advancing Transformer Inference Ability via Head-Specific Complex Vector Attention","date":"2025-05-15","arxiv_id":"2505.10222","repositories_listed":1,"syntology":null},{"url":"/paper/visually-guided-decoding-gradient-free-hard","slug":"visually-guided-decoding-gradient-free-hard","title":"Visually Guided Decoding: Gradient-Free Hard Prompt Inversion with Language Models","date":"2025-05-13","arxiv_id":"2505.08622","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":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) · 1 unverified","sample_list":"/paper/visually-guided-decoding-gradient-free-hard#ran","syntology_url":"https://syntology.ai/paper/2505.08622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.08622"}},"official":{"repos":["DonghoonKim-1938/VGD"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/anatomical-attention-alignment-representation","slug":"anatomical-attention-alignment-representation","title":"Anatomical Attention Alignment representation for Radiology Report Generation","date":"2025-05-12","arxiv_id":"2505.07689","repositories_listed":1,"syntology":null},{"url":"/paper/concept-level-explainability-for-auditing","slug":"concept-level-explainability-for-auditing","title":"Concept-Level Explainability for Auditing & Steering LLM Responses","date":"2025-05-12","arxiv_id":"2505.07610","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/concept-level-explainability-for-auditing#ran","syntology_url":"https://syntology.ai/paper/2505.07610","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.07610"}},"official":{"repos":["k-amara/ConceptX"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mellm-exploring-llm-powered-micro-expression","slug":"mellm-exploring-llm-powered-micro-expression","title":"MELLM: Exploring LLM-Powered Micro-Expression Understanding Enhanced by Subtle Motion Perception","date":"2025-05-11","arxiv_id":"2505.07007","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-fake-news-detection-mfnd-dataset","slug":"multimodal-fake-news-detection-mfnd-dataset","title":"Multimodal Fake News Detection: MFND Dataset and Shallow-Deep Multitask Learning","date":"2025-05-11","arxiv_id":"2505.06796","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-markup-language-generation-for","slug":"adaptive-markup-language-generation-for","title":"Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding","date":"2025-05-08","arxiv_id":"2505.05446","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":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/adaptive-markup-language-generation-for#ran","syntology_url":"https://syntology.ai/paper/2505.05446","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.05446"}},"official":{"repos":["Euphoria16/DocMark"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}}],"record_sha256":"29484400a17fa0e43255d6c5964338f2a58f213ac5fb576e6dc0d91dfa63c0b0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}