{"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/position-wise-feed-forward-layer/papers/63","list_of":"/method/position-wise-feed-forward-layer","method":"Position-Wise Feed-Forward Layer","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":63,"pages_in_order":139,"rows_per_page":100,"rows":[6201,6300],"of":13895,"counts":{"archive_papers_tagged":13895,"with_a_code_link":6514,"where_syntology_ran_a_sample":2229,"not_listed_spam_title":0,"listed":13895,"listed_where_code_ran":2229,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1902,"every_run_a_failure_of_syntologys_instrument":327,"listed_with_a_run_with_no_instrument_failure":1902,"listed_every_run_a_failure_of_syntologys_instrument":327,"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/position-wise-feed-forward-layer","prev":"/method/position-wise-feed-forward-layer/papers/62","next":"/method/position-wise-feed-forward-layer/papers/64","papers":[{"paper":"/paper/gpqa-a-graduate-level-google-proof-q-a","slug":"gpqa-a-graduate-level-google-proof-q-a","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","date":"2023-11-20","arxiv_id":"2311.12022","n_code_links":3,"syntology":{"ran":7,"of":8,"n_ran_checked":7,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["idavidrein/gpqa"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/how-to-use-large-language-models-for-text","slug":"how-to-use-large-language-models-for-text","title":"Towards Human-Level Text Coding with LLMs: The Case of Fatherhood Roles in Public Policy Documents","date":"2023-11-20","arxiv_id":"2311.11844","n_code_links":1,"syntology":null},{"paper":"/paper/lidar-hmr-3d-human-mesh-recovery-from-lidar","slug":"lidar-hmr-3d-human-mesh-recovery-from-lidar","title":"LiDAR-HMR: 3D Human Mesh Recovery from LiDAR","date":"2023-11-20","arxiv_id":"2311.11971","n_code_links":2,"syntology":null},{"paper":"/paper/meta-prompting-for-agi-systems","slug":"meta-prompting-for-agi-systems","title":"Meta Prompting for AI Systems","date":"2023-11-20","arxiv_id":"2311.11482","n_code_links":1,"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":["meta-prompting/meta-prompting"],"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/mgct-mutual-guided-cross-modality-transformer","slug":"mgct-mutual-guided-cross-modality-transformer","title":"MGCT: Mutual-Guided Cross-Modality Transformer for Survival Outcome Prediction using Integrative Histopathology-Genomic Features","date":"2023-11-20","arxiv_id":"2311.11659","n_code_links":1,"syntology":null},{"paper":null,"slug":"pmp-swin-multi-scale-patch-message-passing","title":"PMP-Swin: Multi-Scale Patch Message Passing Swin Transformer for Retinal Disease Classification","date":"2023-11-20","arxiv_id":"2311.11669","n_code_links":0,"syntology":null},{"paper":"/paper/unveiling-the-power-of-self-attention-for","slug":"unveiling-the-power-of-self-attention-for","title":"Unveiling the Power of Self-Attention for Shipping Cost Prediction: The Rate Card Transformer","date":"2023-11-20","arxiv_id":"2311.11694","n_code_links":1,"syntology":null},{"paper":"/paper/which-ai-technique-is-better-to-classify","slug":"which-ai-technique-is-better-to-classify","title":"Which AI Technique Is Better to Classify Requirements? An Experiment with SVM, LSTM, and ChatGPT","date":"2023-11-20","arxiv_id":"2311.11547","n_code_links":1,"syntology":null},{"paper":null,"slug":"inspecting-explainability-of-transformer","title":"Inspecting Explainability of Transformer Models with Additional Statistical Information","date":"2023-11-19","arxiv_id":"2311.11378","n_code_links":0,"syntology":null},{"paper":null,"slug":"behavior-optimized-image-generation","title":"Behavior Optimized Image Generation","date":"2023-11-18","arxiv_id":"2311.10995","n_code_links":0,"syntology":null},{"paper":null,"slug":"partially-randomizing-transformer-weights-for","title":"Partially Randomizing Transformer Weights for Dialogue Response Diversity","date":"2023-11-18","arxiv_id":"2311.10943","n_code_links":0,"syntology":null},{"paper":"/paper/structure-aware-sparse-view-x-ray-3d","slug":"structure-aware-sparse-view-x-ray-3d","title":"Structure-Aware Sparse-View X-ray 3D Reconstruction","date":"2023-11-18","arxiv_id":"2311.10959","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":1,"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":{"repos":["caiyuanhao1998/sax-nerf"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"visual-ai-and-linguistic-intelligence-through","title":"Visual AI and Linguistic Intelligence Through Steerability and Composability","date":"2023-11-18","arxiv_id":"2312.12383","n_code_links":0,"syntology":null},{"paper":null,"slug":"advancements-in-generative-ai-a-comprehensive","title":"Advancements in Generative AI: A Comprehensive Review of GANs, GPT, Autoencoders, Diffusion Model, and Transformers","date":"2023-11-17","arxiv_id":"2311.10242","n_code_links":0,"syntology":null},{"paper":null,"slug":"bias-a-head-analyzing-bias-in-transformer","title":"Bias A-head? Analyzing Bias in Transformer-Based Language Model Attention Heads","date":"2023-11-17","arxiv_id":"2311.10395","n_code_links":0,"syntology":null},{"paper":null,"slug":"eduquick-a-dataset-toward-evaluating","title":"EduQuick: A Dataset Toward Evaluating Summarization of Informal Educational Content for Social Media","date":"2023-11-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/multi-entity-video-transformers-for-fine","slug":"multi-entity-video-transformers-for-fine","title":"Multi-entity Video Transformers for Fine-Grained Video Representation Learning","date":"2023-11-17","arxiv_id":"2311.10873","n_code_links":1,"syntology":null},{"paper":null,"slug":"rethinking-attention-exploring-shallow-feed","title":"Rethinking Attention: Exploring Shallow Feed-Forward Neural Networks as an Alternative to Attention Layers in Transformers","date":"2023-11-17","arxiv_id":"2311.10642","n_code_links":0,"syntology":null},{"paper":null,"slug":"semi-supervised-vit-knowledge-distillation","title":"Semi-supervised ViT knowledge distillation network with style transfer normalization for colorectal liver metastases survival prediction","date":"2023-11-17","arxiv_id":"2311.10305","n_code_links":0,"syntology":null},{"paper":"/paper/taco-enhancing-cross-lingual-transfer-for-low","slug":"taco-enhancing-cross-lingual-transfer-for-low","title":"TaCo: Enhancing Cross-Lingual Transfer for Low-Resource Languages in LLMs through Translation-Assisted Chain-of-Thought Processes","date":"2023-11-17","arxiv_id":"2311.10797","n_code_links":1,"syntology":null},{"paper":"/paper/blt-can-large-language-models-handle-basic","slug":"blt-can-large-language-models-handle-basic","title":"BLT: Can Large Language Models Handle Basic Legal Text?","date":"2023-11-16","arxiv_id":"2311.09693","n_code_links":1,"syntology":null},{"paper":null,"slug":"enchancing-semi-supervised-learning-for","title":"Prompt-based Pseudo-labeling Strategy for Sample-Efficient Semi-Supervised Extractive Summarization","date":"2023-11-16","arxiv_id":"2311.09559","n_code_links":0,"syntology":null},{"paper":"/paper/gee-grammar-error-explanation-with-large","slug":"gee-grammar-error-explanation-with-large","title":"GEE! Grammar Error Explanation with Large Language Models","date":"2023-11-16","arxiv_id":"2311.09517","n_code_links":1,"syntology":null},{"paper":"/paper/huatuogpt-ii-one-stage-training-for-medical","slug":"huatuogpt-ii-one-stage-training-for-medical","title":"HuatuoGPT-II, One-stage Training for Medical Adaption of LLMs","date":"2023-11-16","arxiv_id":"2311.09774","n_code_links":1,"syntology":{"ran":13,"of":14,"n_ran_checked":11,"n_instrument":2,"unverified":1,"pointer_only":14,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["freedomintelligence/huatuogpt-ii"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"human-still-wins-over-llm-an-empirical-study","title":"Human Still Wins over LLM: An Empirical Study of Active Learning on Domain-Specific Annotation Tasks","date":"2023-11-16","arxiv_id":"2311.09825","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-data-contamination-in-modern","title":"Investigating Data Contamination in Modern Benchmarks for Large Language Models","date":"2023-11-16","arxiv_id":"2311.09783","n_code_links":0,"syntology":null},{"paper":"/paper/knowledgemath-knowledge-intensive-math-word","slug":"knowledgemath-knowledge-intensive-math-word","title":"FinanceMath: Knowledge-Intensive Math Reasoning in Finance Domains","date":"2023-11-16","arxiv_id":"2311.09797","n_code_links":1,"syntology":{"ran":12,"of":15,"n_ran_checked":12,"n_instrument":0,"unverified":3,"pointer_only":15,"phrase":"12 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; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["yale-nlp/knowledgemath"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/large-language-models-for-propaganda-span","slug":"large-language-models-for-propaganda-span","title":"Large Language Models for Propaganda Span Annotation","date":"2023-11-16","arxiv_id":"2311.09812","n_code_links":1,"syntology":null},{"paper":null,"slug":"marformer-an-efficient-metal-artifact","title":"MARformer: An Efficient Metal Artifact Reduction Transformer for Dental CBCT Images","date":"2023-11-16","arxiv_id":"2311.09590","n_code_links":0,"syntology":null},{"paper":"/paper/ml-bench-large-language-models-leverage-open","slug":"ml-bench-large-language-models-leverage-open","title":"ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code","date":"2023-11-16","arxiv_id":"2311.09835","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":["gersteinlab/ml-bench"],"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/multi-view-spectrogram-transformer-for","slug":"multi-view-spectrogram-transformer-for","title":"Multi-View Spectrogram Transformer for Respiratory Sound Classification","date":"2023-11-16","arxiv_id":"2311.09655","n_code_links":1,"syntology":null},{"paper":"/paper/neural-logic-human-object-interaction","slug":"neural-logic-human-object-interaction","title":"Neural-Logic Human-Object Interaction Detection","date":"2023-11-16","arxiv_id":"2311.09817","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"on-evaluating-the-integration-of-reasoning","title":"On Evaluating the Integration of Reasoning and Action in LLM Agents with Database Question Answering","date":"2023-11-16","arxiv_id":"2311.09721","n_code_links":0,"syntology":null},{"paper":null,"slug":"psybench-a-balanced-and-in-depth","title":"ConceptPsy:A Benchmark Suite with Conceptual Comprehensiveness in Psychology","date":"2023-11-16","arxiv_id":"2311.09861","n_code_links":0,"syntology":null},{"paper":"/paper/score-a-framework-for-self-contradictory","slug":"score-a-framework-for-self-contradictory","title":"Self-Contradictory Reasoning Evaluation and Detection","date":"2023-11-16","arxiv_id":"2311.09603","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"pointer_only":10,"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) · 2 unverified","official":{"repos":["uscnlp-lime/Self-Contradictory"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/structured-chemistry-reasoning-with-large","slug":"structured-chemistry-reasoning-with-large","title":"Structured Chemistry Reasoning with Large Language Models","date":"2023-11-16","arxiv_id":"2311.09656","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 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ozyyshr/structchem"],"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"]}}},{"paper":"/paper/survtimesurvival-survival-analysis-on-the","slug":"survtimesurvival-survival-analysis-on-the","title":"SurvTimeSurvival: Survival Analysis On The Patient With Multiple Visits/Records","date":"2023-11-16","arxiv_id":"2311.09854","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-autonomous-hypothesis-verification","title":"Towards Autonomous Hypothesis Verification via Language Models with Minimal Guidance","date":"2023-11-16","arxiv_id":"2311.09706","n_code_links":0,"syntology":null},{"paper":"/paper/unifiedvisiongpt-streamlining-vision-oriented","slug":"unifiedvisiongpt-streamlining-vision-oriented","title":"UnifiedVisionGPT: Streamlining Vision-Oriented AI through Generalized Multimodal Framework","date":"2023-11-16","arxiv_id":"2311.10125","n_code_links":1,"syntology":null},{"paper":"/paper/wildfire-smoke-detection-with-cross-contrast","slug":"wildfire-smoke-detection-with-cross-contrast","title":"Wildfire Smoke Detection with Cross Contrast Patch Embedding","date":"2023-11-16","arxiv_id":"2311.10116","n_code_links":1,"syntology":null},{"paper":"/paper/can-large-language-models-follow-concept","slug":"can-large-language-models-follow-concept","title":"Can Large Language Models Follow Concept Annotation Guidelines? A Case Study on Scientific and Financial Domains","date":"2023-11-15","arxiv_id":"2311.08704","n_code_links":1,"syntology":null},{"paper":null,"slug":"comparing-generalization-in-learning-with","title":"Comparing Generalization in Learning with Limited Numbers of Exemplars: Transformer vs. RNN in Attractor Dynamics","date":"2023-11-15","arxiv_id":"2311.10763","n_code_links":0,"syntology":null},{"paper":"/paper/contrastive-transformer-learning-with","slug":"contrastive-transformer-learning-with","title":"Contrastive Transformer Learning with Proximity Data Generation for Text-Based Person Search","date":"2023-11-15","arxiv_id":"2311.09084","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":5,"n_instrument":2,"unverified":0,"pointer_only":7,"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","official":{"repos":["hcplab-sysu/personsearch-ctlg"],"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"]}}},{"paper":null,"slug":"deep-group-interest-modeling-of-full-lifelong","title":"Deep Group Interest Modeling of Full Lifelong User Behaviors for CTR Prediction","date":"2023-11-15","arxiv_id":"2311.10764","n_code_links":0,"syntology":null},{"paper":"/paper/degradation-estimation-recurrent-neural","slug":"degradation-estimation-recurrent-neural","title":"Degradation Estimation Recurrent Neural Network with Local and Non-Local Priors for Compressive Spectral Imaging","date":"2023-11-15","arxiv_id":"2311.08808","n_code_links":1,"syntology":null},{"paper":null,"slug":"dista-denoising-spiking-transformer-with","title":"DISTA: Denoising Spiking Transformer with intrinsic plasticity and spatiotemporal attention","date":"2023-11-15","arxiv_id":"2311.09376","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-machine-translation-through","title":"Enhancing Machine Translation through Advanced In-Context Learning: A Methodological Strategy for GPT-4 Improvement","date":"2023-11-15","arxiv_id":"2311.10765","n_code_links":0,"syntology":null},{"paper":"/paper/factcheck-gpt-end-to-end-fine-grained","slug":"factcheck-gpt-end-to-end-fine-grained","title":"Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers","date":"2023-11-15","arxiv_id":"2311.09000","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["yuxiaw/factcheck-gpt"],"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":"generalizable-imitation-learning-through-pre","title":"Generalizable Imitation Learning Through Pre-Trained Representations","date":"2023-11-15","arxiv_id":"2311.09350","n_code_links":0,"syntology":null},{"paper":null,"slug":"grim-graph-based-interactive-narrative","title":"GENEVA: GENErating and Visualizing branching narratives using LLMs","date":"2023-11-15","arxiv_id":"2311.09213","n_code_links":0,"syntology":null},{"paper":"/paper/i-was-blind-but-now-i-see-implementing-vision","slug":"i-was-blind-but-now-i-see-implementing-vision","title":"I Was Blind but Now I See: Implementing Vision-Enabled Dialogue in Social Robots","date":"2023-11-15","arxiv_id":"2311.08957","n_code_links":1,"syntology":null},{"paper":null,"slug":"jailbreaking-gpt-4v-via-self-adversarial","title":"Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts","date":"2023-11-15","arxiv_id":"2311.09127","n_code_links":0,"syntology":null},{"paper":null,"slug":"llamas-know-what-gpts-don-t-show-surrogate","title":"Llamas Know What GPTs Don't Show: Surrogate Models for Confidence Estimation","date":"2023-11-15","arxiv_id":"2311.08877","n_code_links":0,"syntology":null},{"paper":"/paper/mela-multilingual-evaluation-of-linguistic","slug":"mela-multilingual-evaluation-of-linguistic","title":"MELA: Multilingual Evaluation of Linguistic Acceptability","date":"2023-11-15","arxiv_id":"2311.09033","n_code_links":1,"syntology":null},{"paper":"/paper/progressive-feedback-enhanced-transformer-for","slug":"progressive-feedback-enhanced-transformer-for","title":"Progressive Feedback-Enhanced Transformer for Image Forgery Localization","date":"2023-11-15","arxiv_id":"2311.08910","n_code_links":1,"syntology":null},{"paper":"/paper/safer-instruct-aligning-language-models-with","slug":"safer-instruct-aligning-language-models-with","title":"Safer-Instruct: Aligning Language Models with Automated Preference Data","date":"2023-11-15","arxiv_id":"2311.08685","n_code_links":1,"syntology":null},{"paper":null,"slug":"sparsespikformer-a-co-design-framework-for","title":"SparseSpikformer: A Co-Design Framework for Token and Weight Pruning in Spiking Transformer","date":"2023-11-15","arxiv_id":"2311.08806","n_code_links":0,"syntology":null},{"paper":"/paper/token-prediction-as-implicit-classification","slug":"token-prediction-as-implicit-classification","title":"Token Prediction as Implicit Classification to Identify LLM-Generated Text","date":"2023-11-15","arxiv_id":"2311.08723","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["markchenyutian/t5-sentinel-public"],"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/tooltalk-evaluating-tool-usage-in-a","slug":"tooltalk-evaluating-tool-usage-in-a","title":"ToolTalk: Evaluating Tool-Usage in a Conversational Setting","date":"2023-11-15","arxiv_id":"2311.10775","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":null}},{"paper":null,"slug":"x-eval-generalizable-multi-aspect-text","title":"X-Eval: Generalizable Multi-aspect Text Evaluation via Augmented Instruction Tuning with Auxiliary Evaluation Aspects","date":"2023-11-15","arxiv_id":"2311.08788","n_code_links":0,"syntology":null},{"paper":"/paper/a-wolf-in-sheep-s-clothing-generalized-nested","slug":"a-wolf-in-sheep-s-clothing-generalized-nested","title":"A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily","date":"2023-11-14","arxiv_id":"2311.08268","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":7,"n_instrument":1,"unverified":1,"pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["NJUNLP/ReNeLLM"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/automated-title-and-abstract-screening-for","slug":"automated-title-and-abstract-screening-for","title":"Automated title and abstract screening for scoping reviews using the GPT-4 Large Language Model","date":"2023-11-14","arxiv_id":"2311.07918","n_code_links":1,"syntology":null},{"paper":null,"slug":"comparing-humans-gpt-4-and-gpt-4v-on","title":"Comparing Humans, GPT-4, and GPT-4V On Abstraction and Reasoning Tasks","date":"2023-11-14","arxiv_id":"2311.09247","n_code_links":0,"syntology":null},{"paper":"/paper/contrastive-learning-for-multi-object","slug":"contrastive-learning-for-multi-object","title":"Contrastive Learning for Multi-Object Tracking with Transformers","date":"2023-11-14","arxiv_id":"2311.08043","n_code_links":1,"syntology":null},{"paper":null,"slug":"dual-channel-prototype-network-for-few-shot","title":"Dual-channel Prototype Network for few-shot Classification of Pathological Images","date":"2023-11-14","arxiv_id":"2311.07871","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-llms-on-document-based-qa-exact","title":"Evaluating LLMs on Document-Based QA: Exact Answer Selection and Numerical Extraction using Cogtale dataset","date":"2023-11-14","arxiv_id":"2311.07878","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-semi-supervised-hierarchical","slug":"exploring-semi-supervised-hierarchical","title":"Exploring Semi-supervised Hierarchical Stacked Encoder for Legal Judgement Prediction","date":"2023-11-14","arxiv_id":"2311.08103","n_code_links":1,"syntology":null},{"paper":"/paper/gmtr-graph-matching-transformers","slug":"gmtr-graph-matching-transformers","title":"GMTR: Graph Matching Transformers","date":"2023-11-14","arxiv_id":"2311.08141","n_code_links":1,"syntology":null},{"paper":null,"slug":"how-good-are-large-language-models-on-african","title":"How good are Large Language Models on African Languages?","date":"2023-11-14","arxiv_id":"2311.07978","n_code_links":0,"syntology":null},{"paper":"/paper/magic-benchmarking-large-language-model","slug":"magic-benchmarking-large-language-model","title":"MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration","date":"2023-11-14","arxiv_id":"2311.08562","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":["cathyxl/magic"],"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":null,"slug":"rotation-agnostic-image-representation","title":"Rotation-Agnostic Image Representation Learning for Digital Pathology","date":"2023-11-14","arxiv_id":"2311.08359","n_code_links":0,"syntology":null},{"paper":"/paper/secure-transformer-inference","slug":"secure-transformer-inference","title":"Secure Transformer Inference Protocol","date":"2023-11-14","arxiv_id":"2312.00025","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":1,"n_instrument":3,"unverified":0,"pointer_only":1,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yuanmu97/secure-transformer-inference"],"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","unlocated"]}}},{"paper":null,"slug":"simplesafetytests-a-test-suite-for","title":"SimpleSafetyTests: a Test Suite for Identifying Critical Safety Risks in Large Language Models","date":"2023-11-14","arxiv_id":"2311.08370","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-benchmark-to-understand-the-role-of","title":"A Benchmark to Understand the Role of Knowledge Graphs on Large Language Model's Accuracy for Question Answering on Enterprise SQL Databases","date":"2023-11-13","arxiv_id":"2311.07509","n_code_links":0,"syntology":null},{"paper":"/paper/assessing-logical-puzzle-solving-in-large","slug":"assessing-logical-puzzle-solving-in-large","title":"Assessing Logical Puzzle Solving in Large Language Models: Insights from a Minesweeper Case Study","date":"2023-11-13","arxiv_id":"2311.07387","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":0,"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":["yinghao-li/minesweeper-for-llm"],"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":"cross-axis-transformer-with-2d-rotary","title":"Cross-Axis Transformer with 3D Rotary Positional Embeddings","date":"2023-11-13","arxiv_id":"2311.07184","n_code_links":0,"syntology":null},{"paper":"/paper/fovea-transformer-efficient-long-context","slug":"fovea-transformer-efficient-long-context","title":"Fovea Transformer: Efficient Long-Context Modeling with Structured Fine-to-Coarse Attention","date":"2023-11-13","arxiv_id":"2311.07102","n_code_links":1,"syntology":null},{"paper":null,"slug":"language-grounded-qformer-for-efficient","title":"Semantically Grounded QFormer for Efficient Vision Language Understanding","date":"2023-11-13","arxiv_id":"2311.07449","n_code_links":0,"syntology":null},{"paper":null,"slug":"lm-polygraph-uncertainty-estimation-for","title":"LM-Polygraph: Uncertainty Estimation for Language Models","date":"2023-11-13","arxiv_id":"2311.07383","n_code_links":0,"syntology":null},{"paper":null,"slug":"megaverse-benchmarking-large-language-models","title":"MEGAVERSE: Benchmarking Large Language Models Across Languages, Modalities, Models and Tasks","date":"2023-11-13","arxiv_id":"2311.07463","n_code_links":0,"syntology":null},{"paper":null,"slug":"speech-based-slot-filling-using-large","title":"Speech-based Slot Filling using Large Language Models","date":"2023-11-13","arxiv_id":"2311.07418","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-impact-of-large-language-models-on","title":"The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4","date":"2023-11-13","arxiv_id":"2311.07361","n_code_links":0,"syntology":null},{"paper":"/paper/veritymath-advancing-mathematical-reasoning","slug":"veritymath-advancing-mathematical-reasoning","title":"VerityMath: Advancing Mathematical Reasoning by Self-Verification Through Unit Consistency","date":"2023-11-13","arxiv_id":"2311.07172","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["vernontoh/veritymath"],"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":null,"slug":"controllable-topic-focused-abstractive","title":"Controllable Topic-Focused Abstractive Summarization","date":"2023-11-12","arxiv_id":"2311.06724","n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-and-correcting-hate-speech-in","title":"Detecting and Correcting Hate Speech in Multimodal Memes with Large Visual Language Model","date":"2023-11-12","arxiv_id":"2311.06737","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-gpt-4-for-chest-x-ray","title":"Evaluation of GPT-4 for chest X-ray impression generation: A reader study on performance and perception","date":"2023-11-12","arxiv_id":"2311.06815","n_code_links":0,"syntology":null},{"paper":"/paper/flames-benchmarking-value-alignment-of","slug":"flames-benchmarking-value-alignment-of","title":"Flames: Benchmarking Value Alignment of LLMs in Chinese","date":"2023-11-12","arxiv_id":"2311.06899","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-models-understanding-of-math","title":"Large Language Models' Understanding of Math: Source Criticism and Extrapolation","date":"2023-11-12","arxiv_id":"2311.07618","n_code_links":0,"syntology":null},{"paper":null,"slug":"tsvit-a-time-series-vision-transformer-for","title":"TSViT: A Time Series Vision Transformer for Fault Diagnosis","date":"2023-11-12","arxiv_id":"2311.06916","n_code_links":0,"syntology":null},{"paper":null,"slug":"two-stream-scene-understanding-on-graph","title":"Two Stream Scene Understanding on Graph Embedding","date":"2023-11-12","arxiv_id":"2311.06746","n_code_links":0,"syntology":null},{"paper":"/paper/adversarial-fine-tuning-using-generated","slug":"adversarial-fine-tuning-using-generated","title":"Adversarial Fine-tuning using Generated Respiratory Sound to Address Class Imbalance","date":"2023-11-11","arxiv_id":"2311.06480","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 3 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; every one of the 3 samples that ran constructed an object rather than computing a result","official":{"repos":["kaen2891/adversarial_fine-tuning_using_generated_respiratory_sound"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/cvthead-one-shot-controllable-head-avatar","slug":"cvthead-one-shot-controllable-head-avatar","title":"CVTHead: One-shot Controllable Head Avatar with Vertex-feature Transformer","date":"2023-11-11","arxiv_id":"2311.06443","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":2,"n_instrument":3,"unverified":1,"pointer_only":6,"phrase":"5 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; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["howiema/cvthead"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"intentional-biases-in-llm-responses","title":"Intentional Biases in LLM Responses","date":"2023-11-11","arxiv_id":"2311.07611","n_code_links":0,"syntology":null},{"paper":null,"slug":"sparse-attention-based-neural-networks-for","title":"Sparse Attention-Based Neural Networks for Code Classification","date":"2023-11-11","arxiv_id":"2311.06575","n_code_links":0,"syntology":null},{"paper":"/paper/automatic-report-generation-for","slug":"automatic-report-generation-for","title":"Automatic Report Generation for Histopathology images using pre-trained Vision Transformers","date":"2023-11-10","arxiv_id":"2311.06176","n_code_links":1,"syntology":null},{"paper":"/paper/data-contamination-quiz-a-tool-to-detect-and","slug":"data-contamination-quiz-a-tool-to-detect-and","title":"Data Contamination Quiz: A Tool to Detect and Estimate Contamination in Large Language Models","date":"2023-11-10","arxiv_id":"2311.06233","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":["shahriargolchin/dcq"],"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/dual-input-stream-transformer-for-eye","slug":"dual-input-stream-transformer-for-eye","title":"Dual input stream transformer for vertical drift correction in eye-tracking reading data","date":"2023-11-10","arxiv_id":"2311.06095","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-rock-image-segmentation-in-digital","title":"Enhancing Rock Image Segmentation in Digital Rock Physics: A Fusion of Generative AI and State-of-the-Art Neural Networks","date":"2023-11-10","arxiv_id":"2311.06079","n_code_links":0,"syntology":null},{"paper":null,"slug":"hiformer-heterogeneous-feature-interactions","title":"Hiformer: Heterogeneous Feature Interactions Learning with Transformers for Recommender Systems","date":"2023-11-10","arxiv_id":"2311.05884","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-to-bridge-the-gap-between-modalities-a","title":"How to Bridge the Gap between Modalities: Survey on Multimodal Large Language Model","date":"2023-11-10","arxiv_id":"2311.07594","n_code_links":0,"syntology":null}],"record_sha256":"a03a03eba41640f9c26b9dc539cb8fa5f740678df93dc30e195bf3ae64d26f98","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}