{"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":"/method/softmax/papers/191","list_of":"/method/softmax","method":"Softmax","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":191,"pages_in_order":375,"rows_per_page":100,"rows":[19001,19100],"of":37443,"counts":{"archive_papers_tagged":37443,"with_a_code_link":15869,"where_syntology_ran_a_sample":4578,"not_listed_spam_title":0,"listed":37443,"listed_where_code_ran":4578,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3835,"every_run_a_failure_of_syntologys_instrument":743,"listed_with_a_run_with_no_instrument_failure":3835,"listed_every_run_a_failure_of_syntologys_instrument":743,"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":"/method/softmax","prev":"/method/softmax/papers/190","next":"/method/softmax/papers/192","papers":[{"paper":"/paper/slowformer-universal-adversarial-patch-for","slug":"slowformer-universal-adversarial-patch-for","title":"SlowFormer: Universal Adversarial Patch for Attack on Compute and Energy Efficiency of Inference Efficient Vision Transformers","date":"2023-10-04","arxiv_id":"2310.02544","n_code_links":1,"syntology":null},{"paper":"/paper/t-3-bench-benchmarking-current-progress-in","slug":"t-3-bench-benchmarking-current-progress-in","title":"T$^3$Bench: Benchmarking Current Progress in Text-to-3D Generation","date":"2023-10-04","arxiv_id":"2310.02977","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["THU-LYJ-Lab/T3Bench"],"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"]}}},{"paper":null,"slug":"understanding-in-context-learning-in","title":"Understanding In-Context Learning in Transformers and LLMs by Learning to Learn Discrete Functions","date":"2023-10-04","arxiv_id":"2310.03016","n_code_links":0,"syntology":null},{"paper":null,"slug":"benchmarking-and-improving-generator","title":"Benchmarking and Improving Generator-Validator Consistency of Language Models","date":"2023-10-03","arxiv_id":"2310.01846","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-gpt-4-replicate-empirical-software","title":"Can GPT-4 Replicate Empirical Software Engineering Research?","date":"2023-10-03","arxiv_id":"2310.01727","n_code_links":0,"syntology":null},{"paper":"/paper/can-large-language-models-provide-useful","slug":"can-large-language-models-provide-useful","title":"Can large language models provide useful feedback on research papers? A large-scale empirical analysis","date":"2023-10-03","arxiv_id":"2310.01783","n_code_links":1,"syntology":null},{"paper":"/paper/contrastive-post-training-large-language","slug":"contrastive-post-training-large-language","title":"Automatic Pair Construction for Contrastive Post-training","date":"2023-10-03","arxiv_id":"2310.02263","n_code_links":1,"syntology":null},{"paper":null,"slug":"de-novo-drug-design-with-joint-transformers","title":"De Novo Drug Design with Joint Transformers","date":"2023-10-03","arxiv_id":"2310.02066","n_code_links":0,"syntology":null},{"paper":"/paper/discrete-compositional-and-symbolic","slug":"discrete-compositional-and-symbolic","title":"Discrete, compositional, and symbolic representations through attractor dynamics","date":"2023-10-03","arxiv_id":"2310.01807","n_code_links":1,"syntology":{"ran":2,"of":9,"n_ran_checked":2,"n_instrument":0,"unverified":7,"pointer_only":9,"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) · 7 unverified","official":{"repos":["andrewnam/gfn_attractors"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/ecoassistant-using-llm-assistant-more","slug":"ecoassistant-using-llm-assistant-more","title":"EcoAssistant: Using LLM Assistant More Affordably and Accurately","date":"2023-10-03","arxiv_id":"2310.03046","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"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","official":{"repos":["jieyuz2/ecoassistant"],"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"]}}},{"paper":"/paper/editing-personality-for-llms","slug":"editing-personality-for-llms","title":"Editing Personality for Large Language Models","date":"2023-10-03","arxiv_id":"2310.02168","n_code_links":1,"syntology":null},{"paper":"/paper/halle-switch-rethinking-and-controlling","slug":"halle-switch-rethinking-and-controlling","title":"HallE-Control: Controlling Object Hallucination in Large Multimodal Models","date":"2023-10-03","arxiv_id":"2310.01779","n_code_links":2,"syntology":{"ran":6,"of":9,"n_ran_checked":3,"n_instrument":3,"unverified":3,"pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["bronyayang/HallE_Switch","bronyayang/halle_control"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"harnessing-pre-trained-sentence-transformers","title":"Harnessing Pre-Trained Sentence Transformers for Offensive Language Detection in Indian Languages","date":"2023-10-03","arxiv_id":"2310.02249","n_code_links":0,"syntology":null},{"paper":"/paper/imagenet-ood-deciphering-modern-out-of","slug":"imagenet-ood-deciphering-modern-out-of","title":"ImageNet-OOD: Deciphering Modern Out-of-Distribution Detection Algorithms","date":"2023-10-03","arxiv_id":"2310.01755","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["princetonvisualai/imagenetood"],"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"]}}},{"paper":"/paper/instance-needs-more-care-rewriting-prompts","slug":"instance-needs-more-care-rewriting-prompts","title":"Instances Need More Care: Rewriting Prompts for Instances with LLMs in the Loop Yields Better Zero-Shot Performance","date":"2023-10-03","arxiv_id":"2310.02107","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"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) · 0 unverified","official":{"repos":["salokr/propmted"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"investigating-large-language-models","title":"Investigating Large Language Models' Perception of Emotion Using Appraisal Theory","date":"2023-10-03","arxiv_id":"2310.04450","n_code_links":0,"syntology":null},{"paper":null,"slug":"low-resource-languages-jailbreak-gpt-4","title":"Low-Resource Languages Jailbreak GPT-4","date":"2023-10-03","arxiv_id":"2310.02446","n_code_links":0,"syntology":null},{"paper":"/paper/probabilistically-rewired-message-passing","slug":"probabilistically-rewired-message-passing","title":"Probabilistically Rewired Message-Passing Neural Networks","date":"2023-10-03","arxiv_id":"2310.02156","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":8,"phrase":"6 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; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["chendiqian/PR-MPNN"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"protoner-few-shot-incremental-learning-for","title":"ProtoNER: Few shot Incremental Learning for Named Entity Recognition using Prototypical Networks","date":"2023-10-03","arxiv_id":"2310.02372","n_code_links":0,"syntology":null},{"paper":null,"slug":"reinforcement-learning-from-automatic","title":"Reinforcement Learning from Automatic Feedback for High-Quality Unit Test Generation","date":"2023-10-03","arxiv_id":"2310.02368","n_code_links":0,"syntology":null},{"paper":null,"slug":"residualtransformer-residual-low-rank","title":"ResidualTransformer: Residual Low-Rank Learning with Weight-Sharing for Transformer Layers","date":"2023-10-03","arxiv_id":"2310.02489","n_code_links":0,"syntology":null},{"paper":null,"slug":"scalenet-an-unsupervised-representation","title":"ScaleNet: An Unsupervised Representation Learning Method for Limited Information","date":"2023-10-03","arxiv_id":"2310.02386","n_code_links":0,"syntology":null},{"paper":null,"slug":"secure-and-effective-data-appraisal-for","title":"SelectFormer: Private and Practical Data Selection for Transformers","date":"2023-10-03","arxiv_id":"2310.02373","n_code_links":0,"syntology":null},{"paper":null,"slug":"selective-feature-adapter-for-dense-vision","title":"Selective Feature Adapter for Dense Vision Transformers","date":"2023-10-03","arxiv_id":"2310.01843","n_code_links":0,"syntology":null},{"paper":"/paper/self-taught-optimizer-stop-recursively-self","slug":"self-taught-optimizer-stop-recursively-self","title":"Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation","date":"2023-10-03","arxiv_id":"2310.02304","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["microsoft/stop"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"the-inhibitor-relu-and-addition-based","title":"The Inhibitor: ReLU and Addition-Based Attention for Efficient Transformers","date":"2023-10-03","arxiv_id":"2310.02041","n_code_links":0,"syntology":null},{"paper":null,"slug":"video-transformers-under-occlusion-how","title":"How Physics and Background Attributes Impact Video Transformers in Robotic Manipulation: A Case Study on Planar Pushing","date":"2023-10-03","arxiv_id":"2310.02044","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-s-next-in-affective-modeling-large","title":"What's Next in Affective Modeling? Large Language Models","date":"2023-10-03","arxiv_id":"2310.18322","n_code_links":0,"syntology":null},{"paper":"/paper/closing-the-curious-case-of-neural-text","slug":"closing-the-curious-case-of-neural-text","title":"Closing the Curious Case of Neural Text Degeneration","date":"2023-10-02","arxiv_id":"2310.01693","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["mattf1n/basis-aware-threshold"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"efficient-remote-sensing-segmentation-with","title":"Efficient Remote Sensing Segmentation With Generative Adversarial Transformer","date":"2023-10-02","arxiv_id":"2310.01292","n_code_links":0,"syntology":null},{"paper":"/paper/evolutionary-neural-architecture-search-for-1","slug":"evolutionary-neural-architecture-search-for-1","title":"Evolutionary Neural Architecture Search for Transformer in Knowledge Tracing","date":"2023-10-02","arxiv_id":"2310.01180","n_code_links":1,"syntology":{"ran":11,"of":14,"n_ran_checked":10,"n_instrument":1,"unverified":3,"pointer_only":14,"phrase":"11 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; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["devilyangs/enas-kt"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/gpt-driver-learning-to-drive-with-gpt","slug":"gpt-driver-learning-to-drive-with-gpt","title":"GPT-Driver: Learning to Drive with GPT","date":"2023-10-02","arxiv_id":"2310.01415","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"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) · 0 unverified","official":{"repos":["pointscoder/gpt-driver"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/improving-dialogue-management-quality","slug":"improving-dialogue-management-quality","title":"Improving Dialogue Management: Quality Datasets vs Models","date":"2023-10-02","arxiv_id":"2310.01339","n_code_links":1,"syntology":null},{"paper":"/paper/label-supervised-llama-finetuning","slug":"label-supervised-llama-finetuning","title":"Label Supervised LLaMA Finetuning","date":"2023-10-02","arxiv_id":"2310.01208","n_code_links":2,"syntology":null},{"paper":"/paper/large-language-model-powered-smart-contract","slug":"large-language-model-powered-smart-contract","title":"Large Language Model-Powered Smart Contract Vulnerability Detection: New Perspectives","date":"2023-10-02","arxiv_id":"2310.01152","n_code_links":1,"syntology":null},{"paper":"/paper/linear-attention-is-maybe-all-you-need-to","slug":"linear-attention-is-maybe-all-you-need-to","title":"Linear attention is (maybe) all you need (to understand transformer optimization)","date":"2023-10-02","arxiv_id":"2310.01082","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/llm-lies-hallucinations-are-not-bugs-but","slug":"llm-lies-hallucinations-are-not-bugs-but","title":"LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples","date":"2023-10-02","arxiv_id":"2310.01469","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["pku-yuangroup/hallucination-attack"],"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"]}}},{"paper":null,"slug":"loft-local-proxy-fine-tuning-for-improving","title":"LoFT: Local Proxy Fine-tuning For Improving Transferability Of Adversarial Attacks Against Large Language Model","date":"2023-10-02","arxiv_id":"2310.04445","n_code_links":0,"syntology":null},{"paper":"/paper/making-llama-see-and-draw-with-seed-tokenizer","slug":"making-llama-see-and-draw-with-seed-tokenizer","title":"Making LLaMA SEE and Draw with SEED Tokenizer","date":"2023-10-02","arxiv_id":"2310.01218","n_code_links":1,"syntology":{"ran":8,"of":11,"n_ran_checked":6,"n_instrument":2,"unverified":3,"pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["ailab-cvc/seed"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"melody-conditioned-lyrics-generation-via-fine","title":"Syllable-level lyrics generation from melody exploiting character-level language model","date":"2023-10-02","arxiv_id":"2310.00863","n_code_links":0,"syntology":null},{"paper":null,"slug":"modality-aware-transformer-for-time-series","title":"Modality-aware Transformer for Financial Time series Forecasting","date":"2023-10-02","arxiv_id":"2310.01232","n_code_links":0,"syntology":null},{"paper":null,"slug":"natural-language-models-for-data","title":"Natural Language Models for Data Visualization Utilizing nvBench Dataset","date":"2023-10-02","arxiv_id":"2310.00832","n_code_links":0,"syntology":null},{"paper":null,"slug":"polysketchformer-fast-transformers-via","title":"PolySketchFormer: Fast Transformers via Sketching Polynomial Kernels","date":"2023-10-02","arxiv_id":"2310.01655","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-mobility-modeling-with-graph-a","slug":"revisiting-mobility-modeling-with-graph-a","title":"Revisiting Mobility Modeling with Graph: A Graph Transformer Model for Next Point-of-Interest Recommendation","date":"2023-10-02","arxiv_id":"2310.01224","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["yukayo/mobgt"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/seismogram-transformer-a-generic-deep","slug":"seismogram-transformer-a-generic-deep","title":"SeisT: A foundational deep learning model for earthquake monitoring tasks","date":"2023-10-02","arxiv_id":"2310.01037","n_code_links":1,"syntology":null},{"paper":null,"slug":"self-distilled-masked-attention-guided-masked","title":"Self-distilled Masked Attention guided masked image modeling with noise Regularized Teacher (SMART) for medical image analysis","date":"2023-10-02","arxiv_id":"2310.01209","n_code_links":0,"syntology":null},{"paper":null,"slug":"target-aware-contextual-political-bias","title":"Target-Aware Contextual Political Bias Detection in News","date":"2023-10-02","arxiv_id":"2310.01138","n_code_links":0,"syntology":null},{"paper":"/paper/the-entity-deduction-arena-a-playground-for","slug":"the-entity-deduction-arena-a-playground-for","title":"Probing the Multi-turn Planning Capabilities of LLMs via 20 Question Games","date":"2023-10-02","arxiv_id":"2310.01468","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":3,"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","official":{"repos":["apple/ml-entity-deduction-arena"],"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"]}}},{"paper":"/paper/tram-benchmarking-temporal-reasoning-for","slug":"tram-benchmarking-temporal-reasoning-for","title":"TRAM: Benchmarking Temporal Reasoning for Large Language Models","date":"2023-10-02","arxiv_id":"2310.00835","n_code_links":1,"syntology":null},{"paper":"/paper/transformers-are-efficient-hierarchical","slug":"transformers-are-efficient-hierarchical","title":"Transformers are efficient hierarchical chemical graph learners","date":"2023-10-02","arxiv_id":"2310.01704","n_code_links":1,"syntology":null},{"paper":"/paper/ultrafeedback-boosting-language-models-with","slug":"ultrafeedback-boosting-language-models-with","title":"UltraFeedback: Boosting Language Models with Scaled AI Feedback","date":"2023-10-02","arxiv_id":"2310.01377","n_code_links":4,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"5 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; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["thunlp/ultrafeedback"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/who-is-chatgpt-benchmarking-llms","slug":"who-is-chatgpt-benchmarking-llms","title":"Who is ChatGPT? Benchmarking LLMs' Psychological Portrayal Using PsychoBench","date":"2023-10-02","arxiv_id":"2310.01386","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"pointer_only":6,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["cuhk-arise/psychobench"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-comparative-study-of-training-objectives","slug":"a-comparative-study-of-training-objectives","title":"A Comparative Study of Training Objectives for Clarification Facet Generation","date":"2023-10-01","arxiv_id":"2310.00703","n_code_links":1,"syntology":null},{"paper":null,"slug":"adapting-vision-foundation-models-for-plant","title":"Adapting Vision Foundation Models for Plant Phenotyping","date":"2023-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/analyzing-and-mitigating-object-hallucination","slug":"analyzing-and-mitigating-object-hallucination","title":"Analyzing and Mitigating Object Hallucination in Large Vision-Language Models","date":"2023-10-01","arxiv_id":"2310.00754","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":2,"n_instrument":5,"unverified":1,"pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","official":{"repos":["yiyangzhou/lure"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/booookscore-a-systematic-exploration-of-book","slug":"booookscore-a-systematic-exploration-of-book","title":"BooookScore: A systematic exploration of book-length summarization in the era of LLMs","date":"2023-10-01","arxiv_id":"2310.00785","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"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","official":{"repos":["lilakk/booookscore"],"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"]}}},{"paper":"/paper/injecting-a-structural-inductive-bias-into-a","slug":"injecting-a-structural-inductive-bias-into-a","title":"SIP: Injecting a Structural Inductive Bias into a Seq2Seq Model by Simulation","date":"2023-10-01","arxiv_id":"2310.00796","n_code_links":1,"syntology":null},{"paper":"/paper/joma-demystifying-multilayer-transformers-via","slug":"joma-demystifying-multilayer-transformers-via","title":"JoMA: Demystifying Multilayer Transformers via JOint Dynamics of MLP and Attention","date":"2023-10-01","arxiv_id":"2310.00535","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"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) · 0 unverified","official":{"repos":["facebookresearch/luckmatters"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/patchmixer-a-patch-mixing-architecture-for","slug":"patchmixer-a-patch-mixing-architecture-for","title":"PatchMixer: A Patch-Mixing Architecture for Long-Term Time Series Forecasting","date":"2023-10-01","arxiv_id":"2310.00655","n_code_links":2,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["Zeying-Gong/PatchMixer"],"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"]}}},{"paper":"/paper/pre-training-with-synthetic-data-helps","slug":"pre-training-with-synthetic-data-helps","title":"Pre-training with Synthetic Data Helps Offline Reinforcement Learning","date":"2023-10-01","arxiv_id":"2310.00771","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["victor-wang-902/synthetic-pretrain-rl"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/rolellm-benchmarking-eliciting-and-enhancing","slug":"rolellm-benchmarking-eliciting-and-enhancing","title":"RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models","date":"2023-10-01","arxiv_id":"2310.00746","n_code_links":2,"syntology":null},{"paper":null,"slug":"sparse-backpropagation-for-moe-training","title":"Sparse Backpropagation for MoE Training","date":"2023-10-01","arxiv_id":"2310.00811","n_code_links":0,"syntology":null},{"paper":null,"slug":"testing-the-limits-of-unified-sequence-to","title":"Testing the Limits of Unified Sequence to Sequence LLM Pretraining on Diverse Table Data Tasks","date":"2023-10-01","arxiv_id":"2310.00789","n_code_links":0,"syntology":null},{"paper":"/paper/tigerscore-towards-building-explainable","slug":"tigerscore-towards-building-explainable","title":"TIGERScore: Towards Building Explainable Metric for All Text Generation Tasks","date":"2023-10-01","arxiv_id":"2310.00752","n_code_links":1,"syntology":{"ran":8,"of":11,"n_ran_checked":8,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["TIGER-AI-Lab/TIGERScore"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/automatikz-text-guided-synthesis-of","slug":"automatikz-text-guided-synthesis-of","title":"AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ","date":"2023-09-30","arxiv_id":"2310.00367","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["potamides/automatikz"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"gaze-driven-sentence-simplification-for","title":"Gaze-Driven Sentence Simplification for Language Learners: Enhancing Comprehension and Readability","date":"2023-09-30","arxiv_id":"2310.00355","n_code_links":0,"syntology":null},{"paper":null,"slug":"graph-neural-architecture-search-with-gpt-4","title":"Graph Neural Architecture Search with GPT-4","date":"2023-09-30","arxiv_id":"2310.01436","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-the-efficacy-of-large-language","title":"Investigating the Efficacy of Large Language Models in Reflective Assessment Methods through Chain of Thoughts Prompting","date":"2023-09-30","arxiv_id":"2310.00272","n_code_links":0,"syntology":null},{"paper":"/paper/it-has-to-be-subjective-human-annotator","slug":"it-has-to-be-subjective-human-annotator","title":"It HAS to be Subjective: Human Annotator Simulation via Zero-shot Density Estimation","date":"2023-09-30","arxiv_id":"2310.00486","n_code_links":1,"syntology":null},{"paper":"/paper/measuring-value-understanding-in-language","slug":"measuring-value-understanding-in-language","title":"ValueDCG: Measuring Comprehensive Human Value Understanding Ability of Language Models","date":"2023-09-30","arxiv_id":"2310.00378","n_code_links":1,"syntology":null},{"paper":null,"slug":"mvc-a-multi-task-vision-transformer-network","title":"MVC: A Multi-Task Vision Transformer Network for COVID-19 Diagnosis from Chest X-ray Images","date":"2023-09-30","arxiv_id":"2310.00418","n_code_links":0,"syntology":null},{"paper":"/paper/pixart-a-fast-training-of-diffusion","slug":"pixart-a-fast-training-of-diffusion","title":"PixArt-$α$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","date":"2023-09-30","arxiv_id":"2310.00426","n_code_links":3,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"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) · 1 unverified","official":{"repos":["PixArt-alpha/PixArt-alpha"],"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":["listed","unlocated"]}}},{"paper":null,"slug":"pubic-symphysis-fetal-head-segmentation-using","title":"Pubic Symphysis-Fetal Head Segmentation Using Pure Transformer with Bi-level Routing Attention","date":"2023-09-30","arxiv_id":"2310.00289","n_code_links":0,"syntology":null},{"paper":"/paper/question-answering-model-for-schizophrenia","slug":"question-answering-model-for-schizophrenia","title":"Question-Answering Model for Schizophrenia Symptoms and Their Impact on Daily Life using Mental Health Forums Data","date":"2023-09-30","arxiv_id":"2310.00448","n_code_links":0,"syntology":null},{"paper":"/paper/quiz-an-arbitrary-volumetric-point-matching","slug":"quiz-an-arbitrary-volumetric-point-matching","title":"QUIZ: An Arbitrary Volumetric Point Matching Method for Medical Image Registration","date":"2023-09-30","arxiv_id":"2310.00296","n_code_links":2,"syntology":null},{"paper":"/paper/relbert-embedding-relations-with-language","slug":"relbert-embedding-relations-with-language","title":"RelBERT: Embedding Relations with Language Models","date":"2023-09-30","arxiv_id":"2310.00299","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-objective-function-equality-property-of","title":"The objective function equality property of infoGAN for two-layer network","date":"2023-09-30","arxiv_id":"2310.00443","n_code_links":0,"syntology":null},{"paper":null,"slug":"unlocking-bias-detection-leveraging","title":"Unlocking Bias Detection: Leveraging Transformer-Based Models for Content Analysis","date":"2023-09-30","arxiv_id":"2310.00347","n_code_links":0,"syntology":null},{"paper":null,"slug":"upar-a-kantian-inspired-prompting-framework","title":"UPAR: A Kantian-Inspired Prompting Framework for Enhancing Large Language Model Capabilities","date":"2023-09-30","arxiv_id":"2310.01441","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-large-language-model-approach-to","title":"A Large Language Model Approach to Educational Survey Feedback Analysis","date":"2023-09-29","arxiv_id":"2309.17447","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-evaluation-of-gpt-models-for-phenotype","title":"An evaluation of GPT models for phenotype concept recognition","date":"2023-09-29","arxiv_id":"2309.17169","n_code_links":0,"syntology":null},{"paper":"/paper/benchmarking-the-abilities-of-large-language","slug":"benchmarking-the-abilities-of-large-language","title":"Benchmarking the Abilities of Large Language Models for RDF Knowledge Graph Creation and Comprehension: How Well Do LLMs Speak Turtle?","date":"2023-09-29","arxiv_id":"2309.17122","n_code_links":3,"syntology":null},{"paper":"/paper/craft-customizing-llms-by-creating-and","slug":"craft-customizing-llms-by-creating-and","title":"CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets","date":"2023-09-29","arxiv_id":"2309.17428","n_code_links":2,"syntology":{"ran":0,"of":5,"n_ran_checked":0,"n_instrument":0,"unverified":5,"pointer_only":5,"phrase":"0 ran · 5 unverified","official":{"repos":["lifan-yuan/craft"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":[]}}},{"paper":"/paper/dyval-graph-informed-dynamic-evaluation-of","slug":"dyval-graph-informed-dynamic-evaluation-of","title":"DyVal: Dynamic Evaluation of Large Language Models for Reasoning Tasks","date":"2023-09-29","arxiv_id":"2309.17167","n_code_links":1,"syntology":null},{"paper":"/paper/enhancing-large-language-models-in-coding","slug":"enhancing-large-language-models-in-coding","title":"Enhancing Large Language Models in Coding Through Multi-Perspective Self-Consistency","date":"2023-09-29","arxiv_id":"2309.17272","n_code_links":1,"syntology":{"ran":8,"of":14,"n_ran_checked":7,"n_instrument":1,"unverified":6,"pointer_only":0,"phrase":"8 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; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["skpig/MPSC"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"gsdc-transformer-an-efficient-and-effective","title":"GSDC Transformer: An Efficient and Effective Cue Fusion for Monocular Multi-Frame Depth Estimation","date":"2023-09-29","arxiv_id":"2309.17059","n_code_links":0,"syntology":null},{"paper":null,"slug":"ifast-weakly-supervised-interpretable-face","title":"IFAST: Weakly Supervised Interpretable Face Anti-spoofing from Single-shot Binocular NIR Images","date":"2023-09-29","arxiv_id":"2309.17399","n_code_links":0,"syntology":null},{"paper":null,"slug":"intuitive-or-dependent-investigating-llms","title":"Intuitive or Dependent? Investigating LLMs' Behavior Style to Conflicting Prompts","date":"2023-09-29","arxiv_id":"2309.17415","n_code_links":0,"syntology":null},{"paper":"/paper/llm-deliberation-evaluating-llms-with","slug":"llm-deliberation-evaluating-llms-with","title":"Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation","date":"2023-09-29","arxiv_id":"2309.17234","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["s-abdelnabi/llm-deliberation"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/memory-gym-partially-observable-challenges-to","slug":"memory-gym-partially-observable-challenges-to","title":"Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents","date":"2023-09-29","arxiv_id":"2309.17207","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","official":{"repos":["marcometer/endless-memory-gym"],"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"]}}},{"paper":"/paper/module-wise-training-of-neural-networks-via","slug":"module-wise-training-of-neural-networks-via","title":"Module-wise Training of Neural Networks via the Minimizing Movement Scheme","date":"2023-09-29","arxiv_id":"2309.17357","n_code_links":0,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":null}},{"paper":null,"slug":"multilingual-natural-language-processingmodel","title":"Multilingual Natural Language Processing Model for Radiology Reports -- The Summary is all you need!","date":"2023-09-29","arxiv_id":"2310.00100","n_code_links":0,"syntology":null},{"paper":null,"slug":"revolutionizing-mobile-interaction-enabling-a","title":"Revolutionizing Mobile Interaction: Enabling a 3 Billion Parameter GPT LLM on Mobile","date":"2023-09-29","arxiv_id":"2310.01434","n_code_links":0,"syntology":null},{"paper":"/paper/robots-that-can-see-leveraging-human-pose-for","slug":"robots-that-can-see-leveraging-human-pose-for","title":"Robots That Can See: Leveraging Human Pose for Trajectory Prediction","date":"2023-09-29","arxiv_id":"2309.17209","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","official":{"repos":["google-research/human-scene-transformer"],"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"]}}},{"paper":"/paper/scale-synergized-collaboration-of-asymmetric","slug":"scale-synergized-collaboration-of-asymmetric","title":"SCALE: Synergized Collaboration of Asymmetric Language Translation Engines","date":"2023-09-29","arxiv_id":"2309.17061","n_code_links":1,"syntology":null},{"paper":null,"slug":"scaling-experiments-in-self-supervised-cross","title":"Scaling Experiments in Self-Supervised Cross-Table Representation Learning","date":"2023-09-29","arxiv_id":"2309.17339","n_code_links":0,"syntology":null},{"paper":"/paper/socreval-large-language-models-with-the","slug":"socreval-large-language-models-with-the","title":"SocREval: Large Language Models with the Socratic Method for Reference-Free Reasoning Evaluation","date":"2023-09-29","arxiv_id":"2310.00074","n_code_links":1,"syntology":null},{"paper":null,"slug":"split-and-merge-aligning-position-biases-in","title":"Split and Merge: Aligning Position Biases in LLM-based Evaluators","date":"2023-09-29","arxiv_id":"2310.01432","n_code_links":0,"syntology":null},{"paper":"/paper/suspicion-agent-playing-imperfect-information","slug":"suspicion-agent-playing-imperfect-information","title":"Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4","date":"2023-09-29","arxiv_id":"2309.17277","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["cr-gjx/suspicion-agent"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/tora-a-tool-integrated-reasoning-agent-for","slug":"tora-a-tool-integrated-reasoning-agent-for","title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","date":"2023-09-29","arxiv_id":"2309.17452","n_code_links":1,"syntology":{"ran":11,"of":12,"n_ran_checked":9,"n_instrument":2,"unverified":1,"pointer_only":9,"phrase":"11 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["microsoft/tora"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}}],"record_sha256":"35032f9848328dbf0ad667fea37a82575617b8fcb5ea1a4a72c826df24cce476","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}