{"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/large-language-model/papers/22","list_of":"/task/large-language-model","task":"Large Language Model","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":22,"pages_in_order":61,"rows_per_page":100,"rows":[2101,2200],"of":6097,"counts":{"archive_papers_tagged":6097,"with_a_code_link":2250,"where_syntology_ran_a_sample":801,"not_listed_spam_title":0,"listed":6097,"listed_where_code_ran":801,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":683,"every_run_a_failure_of_syntologys_instrument":118,"listed_with_a_run_with_no_instrument_failure":683,"listed_every_run_a_failure_of_syntologys_instrument":118,"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/large-language-model","prev":"/task/large-language-model/papers/21","next":"/task/large-language-model/papers/23","papers":[{"url":"/paper/robot-task-planning-based-on-large-language","slug":"robot-task-planning-based-on-large-language","title":"Robot Task Planning Based on Large Language Model Representing Knowledge with Directed Graph Structures","date":"2023-06-08","arxiv_id":"2306.05171","repositories_listed":1,"syntology":null},{"url":"/paper/youku-mplug-a-10-million-large-scale-chinese","slug":"youku-mplug-a-10-million-large-scale-chinese","title":"Youku-mPLUG: A 10 Million Large-scale Chinese Video-Language Dataset for Pre-training and Benchmarks","date":"2023-06-07","arxiv_id":"2306.04362","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"9 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; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/youku-mplug-a-10-million-large-scale-chinese#ran","syntology_url":"https://syntology.ai/paper/2306.04362","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.04362"}},"official":{"repos":["x-plug/youku-mplug"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/recagent-a-novel-simulation-paradigm-for","slug":"recagent-a-novel-simulation-paradigm-for","title":"User Behavior Simulation with Large Language Model based Agents","date":"2023-06-05","arxiv_id":"2306.02552","repositories_listed":1,"syntology":null},{"url":"/paper/spqr-a-sparse-quantized-representation-for","slug":"spqr-a-sparse-quantized-representation-for","title":"SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression","date":"2023-06-05","arxiv_id":"2306.03078","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"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","sample_list":"/paper/spqr-a-sparse-quantized-representation-for#ran","syntology_url":"https://syntology.ai/paper/2306.03078","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.03078"}},"official":{"repos":["vahe1994/spqr"],"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","unlocated"]}}},{"url":"/paper/large-language-model-augmented-narrative","slug":"large-language-model-augmented-narrative","title":"Large Language Model Augmented Narrative Driven Recommendations","date":"2023-06-04","arxiv_id":"2306.02250","repositories_listed":1,"syntology":null},{"url":"/paper/an-evaluation-of-log-parsing-with-chatgpt","slug":"an-evaluation-of-log-parsing-with-chatgpt","title":"Log Parsing: How Far Can ChatGPT Go?","date":"2023-06-02","arxiv_id":"2306.01590","repositories_listed":1,"syntology":null},{"url":"/paper/an-invariant-learning-characterization-of","slug":"an-invariant-learning-characterization-of","title":"An Invariant Learning Characterization of Controlled Text Generation","date":"2023-05-31","arxiv_id":"2306.00198","repositories_listed":1,"syntology":null},{"url":"/paper/idas-intent-discovery-with-abstractive","slug":"idas-intent-discovery-with-abstractive","title":"IDAS: Intent Discovery with Abstractive Summarization","date":"2023-05-31","arxiv_id":"2305.19783","repositories_listed":1,"syntology":null},{"url":"/paper/gpt4tools-teaching-large-language-model-to","slug":"gpt4tools-teaching-large-language-model-to","title":"GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction","date":"2023-05-30","arxiv_id":"2305.18752","repositories_listed":1,"syntology":null},{"url":"/paper/instructedit-improving-automatic-masks-for","slug":"instructedit-improving-automatic-masks-for","title":"InstructEdit: Improving Automatic Masks for Diffusion-based Image Editing With User Instructions","date":"2023-05-29","arxiv_id":"2305.18047","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/instructedit-improving-automatic-masks-for#ran","syntology_url":"https://syntology.ai/paper/2305.18047","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18047"}},"official":{"repos":["qianwangx/instructedit"],"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"]}}},{"url":"/paper/large-language-models-are-not-fair-evaluators","slug":"large-language-models-are-not-fair-evaluators","title":"Large Language Models are not Fair Evaluators","date":"2023-05-29","arxiv_id":"2305.17926","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/large-language-models-are-not-fair-evaluators#ran","syntology_url":"https://syntology.ai/paper/2305.17926","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.17926"}},"official":{"repos":["i-eval/faireval"],"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/leveraging-training-data-in-few-shot","slug":"leveraging-training-data-in-few-shot","title":"Leveraging Training Data in Few-Shot Prompting for Numerical Reasoning","date":"2023-05-29","arxiv_id":"2305.18170","repositories_listed":1,"syntology":null},{"url":"/paper/the-rise-of-ai-language-pathologists","slug":"the-rise-of-ai-language-pathologists","title":"The Rise of AI Language Pathologists: Exploring Two-level Prompt Learning for Few-shot Weakly-supervised Whole Slide Image Classification","date":"2023-05-29","arxiv_id":"2305.17891","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":2,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":6,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/the-rise-of-ai-language-pathologists#ran","syntology_url":"https://syntology.ai/paper/2305.17891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.17891"}},"official":{"repos":["miccaiif/top"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/fusecap-leveraging-large-language-models-to","slug":"fusecap-leveraging-large-language-models-to","title":"FuseCap: Leveraging Large Language Models for Enriched Fused Image Captions","date":"2023-05-28","arxiv_id":"2305.17718","repositories_listed":1,"syntology":null},{"url":"/paper/kosbi-a-dataset-for-mitigating-social-bias","slug":"kosbi-a-dataset-for-mitigating-social-bias","title":"KoSBi: A Dataset for Mitigating Social Bias Risks Towards Safer Large Language Model Application","date":"2023-05-28","arxiv_id":"2305.17701","repositories_listed":1,"syntology":null},{"url":"/paper/learning-a-structural-causal-model-for","slug":"learning-a-structural-causal-model-for","title":"Learning a Structural Causal Model for Intuition Reasoning in Conversation","date":"2023-05-28","arxiv_id":"2305.17727","repositories_listed":1,"syntology":null},{"url":"/paper/datachat-prototyping-a-conversational-agent","slug":"datachat-prototyping-a-conversational-agent","title":"DataChat: Prototyping a Conversational Agent for Dataset Search and Visualization","date":"2023-05-26","arxiv_id":"2305.18358","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-domain-knowledge-for-inclusive-and","slug":"leveraging-domain-knowledge-for-inclusive-and","title":"Leveraging Domain Knowledge for Inclusive and Bias-aware Humanitarian Response Entry Classification","date":"2023-05-26","arxiv_id":"2305.16756","repositories_listed":1,"syntology":null},{"url":"/paper/llms-and-the-abstraction-and-reasoning-corpus","slug":"llms-and-the-abstraction-and-reasoning-corpus","title":"LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representations","date":"2023-05-26","arxiv_id":"2305.18354","repositories_listed":1,"syntology":null},{"url":"/paper/chatbridge-bridging-modalities-with-large","slug":"chatbridge-bridging-modalities-with-large","title":"ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst","date":"2023-05-25","arxiv_id":"2305.16103","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"7 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; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/chatbridge-bridging-modalities-with-large#ran","syntology_url":"https://syntology.ai/paper/2305.16103","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16103"}},"official":null}},{"url":"/paper/generatect-text-guided-3d-chest-ct-generation","slug":"generatect-text-guided-3d-chest-ct-generation","title":"GenerateCT: Text-Conditional Generation of 3D Chest CT Volumes","date":"2023-05-25","arxiv_id":"2305.16037","repositories_listed":1,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":13,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":4,"n_no_contract":8,"n_pointer_only":5,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 4 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/generatect-text-guided-3d-chest-ct-generation#ran","syntology_url":"https://syntology.ai/paper/2305.16037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16037"}},"official":{"repos":["ibrahimethemhamamci/generatect"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/rewritelm-an-instruction-tuned-large-language","slug":"rewritelm-an-instruction-tuned-large-language","title":"RewriteLM: An Instruction-Tuned Large Language Model for Text Rewriting","date":"2023-05-25","arxiv_id":"2305.15685","repositories_listed":1,"syntology":null},{"url":"/paper/beamsearchqa-large-language-models-are-strong","slug":"beamsearchqa-large-language-models-are-strong","title":"Allies: Prompting Large Language Model with Beam Search","date":"2023-05-24","arxiv_id":"2305.14766","repositories_listed":1,"syntology":{"n":13,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"5 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; 1 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/beamsearchqa-large-language-models-are-strong#ran","syntology_url":"https://syntology.ai/paper/2305.14766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14766"}},"official":{"repos":["microsoft/simxns"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/clusterllm-large-language-models-as-a-guide","slug":"clusterllm-large-language-models-as-a-guide","title":"ClusterLLM: Large Language Models as a Guide for Text Clustering","date":"2023-05-24","arxiv_id":"2305.14871","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/clusterllm-large-language-models-as-a-guide#ran","syntology_url":"https://syntology.ai/paper/2305.14871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14871"}},"official":{"repos":["zhang-yu-wei/clusterllm"],"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/estimating-large-language-model-capabilities","slug":"estimating-large-language-model-capabilities","title":"Estimating Large Language Model Capabilities without Labeled Test Data","date":"2023-05-24","arxiv_id":"2305.14802","repositories_listed":1,"syntology":null},{"url":"/paper/gorilla-large-language-model-connected-with","slug":"gorilla-large-language-model-connected-with","title":"Gorilla: Large Language Model Connected with Massive APIs","date":"2023-05-24","arxiv_id":"2305.15334","repositories_listed":1,"syntology":null},{"url":"/paper/how-predictable-are-large-language-model","slug":"how-predictable-are-large-language-model","title":"How Predictable Are Large Language Model Capabilities? A Case Study on BIG-bench","date":"2023-05-24","arxiv_id":"2305.14947","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"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","sample_list":"/paper/how-predictable-are-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2305.14947","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14947"}},"official":{"repos":["ink-usc/predicting-big-bench"],"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"]}}},{"url":"/paper/llmdet-a-large-language-models-detection-tool","slug":"llmdet-a-large-language-models-detection-tool","title":"LLMDet: A Third Party Large Language Models Generated Text Detection Tool","date":"2023-05-24","arxiv_id":"2305.15004","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/llmdet-a-large-language-models-detection-tool#ran","syntology_url":"https://syntology.ai/paper/2305.15004","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15004"}},"official":{"repos":["trustedllm/llmdet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/pivoine-instruction-tuning-for-open-world","slug":"pivoine-instruction-tuning-for-open-world","title":"PIVOINE: Instruction Tuning for Open-world Information Extraction","date":"2023-05-24","arxiv_id":"2305.14898","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/pivoine-instruction-tuning-for-open-world#ran","syntology_url":"https://syntology.ai/paper/2305.14898","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14898"}},"official":{"repos":["lukeming-tsinghua/instruction-tuning-for-open-world-ie"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/prompt-optimization-of-large-language-model","slug":"prompt-optimization-of-large-language-model","title":"AutoPlan: Automatic Planning of Interactive Decision-Making Tasks With Large Language Models","date":"2023-05-24","arxiv_id":"2305.15064","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"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) · 2 unverified","sample_list":"/paper/prompt-optimization-of-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2305.15064","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15064"}},"official":{"repos":["owaski/autoplan"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/spring-gpt-4-out-performs-rl-algorithms-by","slug":"spring-gpt-4-out-performs-rl-algorithms-by","title":"SPRING: Studying the Paper and Reasoning to Play Games","date":"2023-05-24","arxiv_id":"2305.15486","repositories_listed":1,"syntology":null},{"url":"/paper/think-before-you-act-decision-transformers","slug":"think-before-you-act-decision-transformers","title":"Think Before You Act: Decision Transformers with Working Memory","date":"2023-05-24","arxiv_id":"2305.16338","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":3,"n_ran_checked":5,"n_instrument":2,"n_unverified":5,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"7 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/think-before-you-act-decision-transformers#ran","syntology_url":"https://syntology.ai/paper/2305.16338","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16338"}},"official":{"repos":["luciferkonn/dt_mem"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":3,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/this-land-is-your-my-land-evaluating","slug":"this-land-is-your-my-land-evaluating","title":"This Land is {Your, My} Land: Evaluating Geopolitical Biases in Language Models","date":"2023-05-24","arxiv_id":"2305.14610","repositories_listed":1,"syntology":null},{"url":"/paper/2305-14585","slug":"2305-14585","title":"Faithful and Efficient Explanations for Neural Networks via Neural Tangent Kernel Surrogate Models","date":"2023-05-23","arxiv_id":"2305.14585","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":2,"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/2305-14585#ran","syntology_url":"https://syntology.ai/paper/2305.14585","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14585"}},"official":{"repos":["pnnl/projection_ntk"],"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/automatic-model-selection-with-large-language","slug":"automatic-model-selection-with-large-language","title":"Automatic Model Selection with Large Language Models for Reasoning","date":"2023-05-23","arxiv_id":"2305.14333","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/automatic-model-selection-with-large-language#ran","syntology_url":"https://syntology.ai/paper/2305.14333","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14333"}},"official":{"repos":["xuzhao0/model-selection-reasoning"],"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/exploring-contrast-consistency-of-open-domain","slug":"exploring-contrast-consistency-of-open-domain","title":"Exploring Contrast Consistency of Open-Domain Question Answering Systems on Minimally Edited Questions","date":"2023-05-23","arxiv_id":"2305.14441","repositories_listed":1,"syntology":null},{"url":"/paper/learn-from-mistakes-through-cooperative","slug":"learn-from-mistakes-through-cooperative","title":"Learning from Mistakes via Cooperative Study Assistant for Large Language Models","date":"2023-05-23","arxiv_id":"2305.13829","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"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) · 2 unverified","sample_list":"/paper/learn-from-mistakes-through-cooperative#ran","syntology_url":"https://syntology.ai/paper/2305.13829","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13829"}},"official":{"repos":["dqwang122/salam"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/making-the-implicit-explicit-implicit-content","slug":"making-the-implicit-explicit-implicit-content","title":"Natural Language Decompositions of Implicit Content Enable Better Text Representations","date":"2023-05-23","arxiv_id":"2305.14583","repositories_listed":1,"syntology":null},{"url":"/paper/mathdial-a-dialogue-tutoring-dataset-with","slug":"mathdial-a-dialogue-tutoring-dataset-with","title":"MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems","date":"2023-05-23","arxiv_id":"2305.14536","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mathdial-a-dialogue-tutoring-dataset-with#ran","syntology_url":"https://syntology.ai/paper/2305.14536","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14536"}},"official":{"repos":["eth-nlped/mathdial"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/preserving-knowledge-invariance-rethinking","slug":"preserving-knowledge-invariance-rethinking","title":"Preserving Knowledge Invariance: Rethinking Robustness Evaluation of Open Information Extraction","date":"2023-05-23","arxiv_id":"2305.13981","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/preserving-knowledge-invariance-rethinking#ran","syntology_url":"https://syntology.ai/paper/2305.13981","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13981"}},"official":{"repos":["qijimrc/robust"],"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"]}}},{"url":"/paper/prompt-based-monte-carlo-tree-search-for-goal","slug":"prompt-based-monte-carlo-tree-search-for-goal","title":"Prompt-Based Monte-Carlo Tree Search for Goal-Oriented Dialogue Policy Planning","date":"2023-05-23","arxiv_id":"2305.13660","repositories_listed":1,"syntology":{"n":6,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"0 ran · 6 unverified","sample_list":"/paper/prompt-based-monte-carlo-tree-search-for-goal#ran","syntology_url":"https://syntology.ai/paper/2305.13660","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13660"}},"official":{"repos":["jasonyux/gdpzero"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":6,"ran_from_kinds":[]}}},{"url":"/paper/when-the-music-stops-tip-of-the-tongue","slug":"when-the-music-stops-tip-of-the-tongue","title":"When the Music Stops: Tip-of-the-Tongue Retrieval for Music","date":"2023-05-23","arxiv_id":"2305.14072","repositories_listed":1,"syntology":null},{"url":"/paper/wikichat-a-few-shot-llm-based-chatbot","slug":"wikichat-a-few-shot-llm-based-chatbot","title":"WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia","date":"2023-05-23","arxiv_id":"2305.14292","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_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","sample_list":"/paper/wikichat-a-few-shot-llm-based-chatbot#ran","syntology_url":"https://syntology.ai/paper/2305.14292","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14292"}},"official":{"repos":["stanford-oval/wikichat"],"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"]}}},{"url":"/paper/a-study-of-generative-large-language-model","slug":"a-study-of-generative-large-language-model","title":"A Study of Generative Large Language Model for Medical Research and Healthcare","date":"2023-05-22","arxiv_id":"2305.13523","repositories_listed":1,"syntology":null},{"url":"/paper/chain-of-knowledge-a-framework-for-grounding","slug":"chain-of-knowledge-a-framework-for-grounding","title":"Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources","date":"2023-05-22","arxiv_id":"2305.13269","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/chain-of-knowledge-a-framework-for-grounding#ran","syntology_url":"https://syntology.ai/paper/2305.13269","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13269"}},"official":{"repos":["damo-nlp-sg/chain-of-knowledge"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/distilling-chatgpt-for-explainable-automated","slug":"distilling-chatgpt-for-explainable-automated","title":"Distilling ChatGPT for Explainable Automated Student Answer Assessment","date":"2023-05-22","arxiv_id":"2305.12962","repositories_listed":1,"syntology":null},{"url":"/paper/lion-adversarial-distillation-of-closed","slug":"lion-adversarial-distillation-of-closed","title":"Lion: Adversarial Distillation of Proprietary Large Language Models","date":"2023-05-22","arxiv_id":"2305.12870","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"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, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/lion-adversarial-distillation-of-closed#ran","syntology_url":"https://syntology.ai/paper/2305.12870","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.12870"}},"official":{"repos":["yjiangcm/lion"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/making-language-models-better-tool-learners","slug":"making-language-models-better-tool-learners","title":"Making Language Models Better Tool Learners with Execution Feedback","date":"2023-05-22","arxiv_id":"2305.13068","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"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","sample_list":"/paper/making-language-models-better-tool-learners#ran","syntology_url":"https://syntology.ai/paper/2305.13068","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13068"}},"official":{"repos":["zjunlp/trice"],"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","unlocated"]}}},{"url":"/paper/contrastive-learning-with-logic-driven-data","slug":"contrastive-learning-with-logic-driven-data","title":"Abstract Meaning Representation-Based Logic-Driven Data Augmentation for Logical Reasoning","date":"2023-05-21","arxiv_id":"2305.12599","repositories_listed":1,"syntology":null},{"url":"/paper/collaborative-development-of-nlp-models","slug":"collaborative-development-of-nlp-models","title":"Collaborative Development of NLP models","date":"2023-05-20","arxiv_id":"2305.12219","repositories_listed":1,"syntology":null},{"url":"/paper/empower-large-language-model-to-perform","slug":"empower-large-language-model-to-perform","title":"Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answering","date":"2023-05-19","arxiv_id":"2305.11541","repositories_listed":1,"syntology":null},{"url":"/paper/instruct2act-mapping-multi-modality","slug":"instruct2act-mapping-multi-modality","title":"Instruct2Act: Mapping Multi-modality Instructions to Robotic Actions with Large Language Model","date":"2023-05-18","arxiv_id":"2305.11176","repositories_listed":1,"syntology":null},{"url":"/paper/listen-think-and-understand","slug":"listen-think-and-understand","title":"Listen, Think, and Understand","date":"2023-05-18","arxiv_id":"2305.10790","repositories_listed":1,"syntology":null},{"url":"/paper/speechgpt-empowering-large-language-models","slug":"speechgpt-empowering-large-language-models","title":"SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities","date":"2023-05-18","arxiv_id":"2305.11000","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/speechgpt-empowering-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2305.11000","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11000"}},"official":{"repos":["0nutation/speechgpt"],"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/coedit-text-editing-by-task-specific","slug":"coedit-text-editing-by-task-specific","title":"CoEdIT: Text Editing by Task-Specific Instruction Tuning","date":"2023-05-17","arxiv_id":"2305.09857","repositories_listed":1,"syntology":null},{"url":"/paper/structgpt-a-general-framework-for-large","slug":"structgpt-a-general-framework-for-large","title":"StructGPT: A General Framework for Large Language Model to Reason over Structured Data","date":"2023-05-16","arxiv_id":"2305.09645","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":2,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":3,"n_no_contract":5,"n_pointer_only":1,"phrase":"8 ran (of which 2 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 3 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/structgpt-a-general-framework-for-large#ran","syntology_url":"https://syntology.ai/paper/2305.09645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.09645"}},"official":{"repos":["rucaibox/structgpt"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":2,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-model-guided-tree-of-thought","slug":"large-language-model-guided-tree-of-thought","title":"Large Language Model Guided Tree-of-Thought","date":"2023-05-15","arxiv_id":"2305.08291","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/large-language-model-guided-tree-of-thought#ran","syntology_url":"https://syntology.ai/paper/2305.08291","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.08291"}},"official":{"repos":["jieyilong/tree-of-thought-puzzle-solver"],"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/scalable-educational-question-generation-with","slug":"scalable-educational-question-generation-with","title":"Scalable Educational Question Generation with Pre-trained Language Models","date":"2023-05-13","arxiv_id":"2305.07871","repositories_listed":1,"syntology":null},{"url":"/paper/is-chatgpt-fair-for-recommendation-evaluating","slug":"is-chatgpt-fair-for-recommendation-evaluating","title":"Is ChatGPT Fair for Recommendation? Evaluating Fairness in Large Language Model Recommendation","date":"2023-05-12","arxiv_id":"2305.07609","repositories_listed":1,"syntology":null},{"url":"/paper/text2cohort-democratizing-the-nci-imaging","slug":"text2cohort-democratizing-the-nci-imaging","title":"Text2Cohort: Facilitating Intuitive Access to Biomedical Data with Natural Language Cohort Discovery","date":"2023-05-12","arxiv_id":"2305.07637","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-evaluation-of-attribution-by-large","slug":"automatic-evaluation-of-attribution-by-large","title":"Automatic Evaluation of Attribution by Large Language Models","date":"2023-05-10","arxiv_id":"2305.06311","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/automatic-evaluation-of-attribution-by-large#ran","syntology_url":"https://syntology.ai/paper/2305.06311","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.06311"}},"official":{"repos":["osu-nlp-group/attrscore"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/bot-or-human-detecting-chatgpt-imposters-with","slug":"bot-or-human-detecting-chatgpt-imposters-with","title":"Bot or Human? Detecting ChatGPT Imposters with A Single Question","date":"2023-05-10","arxiv_id":"2305.06424","repositories_listed":1,"syntology":null},{"url":"/paper/refining-the-responses-of-llms-by-themselves","slug":"refining-the-responses-of-llms-by-themselves","title":"Refining the Responses of LLMs by Themselves","date":"2023-05-06","arxiv_id":"2305.04039","repositories_listed":1,"syntology":null},{"url":"/paper/lmeye-an-interactive-perception-network-for","slug":"lmeye-an-interactive-perception-network-for","title":"LMEye: An Interactive Perception Network for Large Language Models","date":"2023-05-05","arxiv_id":"2305.03701","repositories_listed":1,"syntology":null},{"url":"/paper/t-sciq-teaching-multimodal-chain-of-thought","slug":"t-sciq-teaching-multimodal-chain-of-thought","title":"T-SciQ: Teaching Multimodal Chain-of-Thought Reasoning via Mixed Large Language Model Signals for Science Question Answering","date":"2023-05-05","arxiv_id":"2305.03453","repositories_listed":1,"syntology":null},{"url":"/paper/2x-faster-language-model-pre-training-via","slug":"2x-faster-language-model-pre-training-via","title":"Masked Structural Growth for 2x Faster Language Model Pre-training","date":"2023-05-04","arxiv_id":"2305.02869","repositories_listed":1,"syntology":{"n":34,"n_ran":16,"n_constructed":6,"n_ran_checked":10,"n_instrument":6,"n_unverified":18,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"16 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 18 unverified","sample_list":"/paper/2x-faster-language-model-pre-training-via#ran","syntology_url":"https://syntology.ai/paper/2305.02869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.02869"}},"official":{"repos":["cofe-ai/msg"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":6,"n_ran_no_instrument_failure":10,"n_unverified":18,"ran_from_kinds":["official"]}}},{"url":"/paper/chatgpt-steered-editing-instructor-for","slug":"chatgpt-steered-editing-instructor-for","title":"Personalized Abstractive Summarization by Tri-agent Generation Pipeline","date":"2023-05-04","arxiv_id":"2305.02483","repositories_listed":1,"syntology":null},{"url":"/paper/improving-code-example-recommendations-on","slug":"improving-code-example-recommendations-on","title":"Improving Code Example Recommendations on Informal Documentation Using BERT and Query-Aware LSH: A Comparative Study","date":"2023-05-04","arxiv_id":"2305.03017","repositories_listed":1,"syntology":null},{"url":"/paper/chatgraph-interpretable-text-classification","slug":"chatgraph-interpretable-text-classification","title":"ChatGraph: Interpretable Text Classification by Converting ChatGPT Knowledge to Graphs","date":"2023-05-03","arxiv_id":"2305.03513","repositories_listed":1,"syntology":null},{"url":"/paper/tallrec-an-effective-and-efficient-tuning","slug":"tallrec-an-effective-and-efficient-tuning","title":"TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation","date":"2023-04-30","arxiv_id":"2305.00447","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/tallrec-an-effective-and-efficient-tuning#ran","syntology_url":"https://syntology.ai/paper/2305.00447","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.00447"}},"official":{"repos":["sai990323/tallrec"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/search-in-the-chain-towards-the-accurate","slug":"search-in-the-chain-towards-the-accurate","title":"Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive Tasks","date":"2023-04-28","arxiv_id":"2304.14732","repositories_listed":1,"syntology":null},{"url":"/paper/towards-autonomous-system-flexible-modular","slug":"towards-autonomous-system-flexible-modular","title":"Towards autonomous system: flexible modular production system enhanced with large language model agents","date":"2023-04-28","arxiv_id":"2304.14721","repositories_listed":1,"syntology":null},{"url":"/paper/swectrl-mini-a-data-transparent-transformer","slug":"swectrl-mini-a-data-transparent-transformer","title":"SweCTRL-Mini: a data-transparent Transformer-based large language model for controllable text generation in Swedish","date":"2023-04-27","arxiv_id":"2304.13994","repositories_listed":1,"syntology":null},{"url":"/paper/uio-at-semeval-2023-task-12-multilingual-fine","slug":"uio-at-semeval-2023-task-12-multilingual-fine","title":"UIO at SemEval-2023 Task 12: Multilingual fine-tuning for sentiment classification in low-resource languages","date":"2023-04-27","arxiv_id":"2304.14189","repositories_listed":1,"syntology":null},{"url":"/paper/unleashing-infinite-length-input-capacity-for","slug":"unleashing-infinite-length-input-capacity-for","title":"Enhancing Large Language Model with Self-Controlled Memory Framework","date":"2023-04-26","arxiv_id":"2304.13343","repositories_listed":1,"syntology":{"n":14,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/unleashing-infinite-length-input-capacity-for#ran","syntology_url":"https://syntology.ai/paper/2304.13343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.13343"}},"official":{"repos":["wbbeyourself/scm4llms"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":11,"ran_from_kinds":["official"]}}},{"url":"/paper/a-lightweight-constrained-generation","slug":"a-lightweight-constrained-generation","title":"A Lightweight Constrained Generation Alternative for Query-focused Summarization","date":"2023-04-23","arxiv_id":"2304.11721","repositories_listed":1,"syntology":null},{"url":"/paper/phoenix-democratizing-chatgpt-across","slug":"phoenix-democratizing-chatgpt-across","title":"Phoenix: Democratizing ChatGPT across Languages","date":"2023-04-20","arxiv_id":"2304.10453","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"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","sample_list":"/paper/phoenix-democratizing-chatgpt-across#ran","syntology_url":"https://syntology.ai/paper/2304.10453","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.10453"}},"official":{"repos":["freedomintelligence/llmzoo"],"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"]}}},{"url":"/paper/a-comparative-study-between-full-parameter","slug":"a-comparative-study-between-full-parameter","title":"A Comparative Study between Full-Parameter and LoRA-based Fine-Tuning on Chinese Instruction Data for Instruction Following Large Language Model","date":"2023-04-17","arxiv_id":"2304.08109","repositories_listed":1,"syntology":null},{"url":"/paper/skillgpt-a-restful-api-service-for-skill","slug":"skillgpt-a-restful-api-service-for-skill","title":"SkillGPT: a RESTful API service for skill extraction and standardization using a Large Language Model","date":"2023-04-17","arxiv_id":"2304.11060","repositories_listed":1,"syntology":null},{"url":"/paper/openassistant-conversations-democratizing","slug":"openassistant-conversations-democratizing","title":"OpenAssistant Conversations -- Democratizing Large Language Model Alignment","date":"2023-04-14","arxiv_id":"2304.07327","repositories_listed":1,"syntology":null},{"url":"/paper/rrhf-rank-responses-to-align-language-models","slug":"rrhf-rank-responses-to-align-language-models","title":"RRHF: Rank Responses to Align Language Models with Human Feedback without tears","date":"2023-04-11","arxiv_id":"2304.05302","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/rrhf-rank-responses-to-align-language-models#ran","syntology_url":"https://syntology.ai/paper/2304.05302","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.05302"}},"official":{"repos":["ganjinzero/rrhf"],"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/graph-toolformer-to-empower-llms-with-graph","slug":"graph-toolformer-to-empower-llms-with-graph","title":"Graph-ToolFormer: To Empower LLMs with Graph Reasoning Ability via Prompt Dataset Augmented by ChatGPT","date":"2023-04-10","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/graph-toolformer-to-empower-llms-with-graph-1","slug":"graph-toolformer-to-empower-llms-with-graph-1","title":"Graph-ToolFormer: To Empower LLMs with Graph Reasoning Ability via Prompt Augmented by ChatGPT","date":"2023-04-10","arxiv_id":"2304.11116","repositories_listed":1,"syntology":null},{"url":"/paper/dera-enhancing-large-language-model","slug":"dera-enhancing-large-language-model","title":"DERA: Enhancing Large Language Model Completions with Dialog-Enabled Resolving Agents","date":"2023-03-30","arxiv_id":"2303.17071","repositories_listed":1,"syntology":null},{"url":"/paper/language-models-can-solve-computer-tasks","slug":"language-models-can-solve-computer-tasks","title":"Language Models can Solve Computer Tasks","date":"2023-03-30","arxiv_id":"2303.17491","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/language-models-can-solve-computer-tasks#ran","syntology_url":"https://syntology.ai/paper/2303.17491","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17491"}},"official":{"repos":["posgnu/rci-agent"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/zero-shot-clinical-entity-recognition-using","slug":"zero-shot-clinical-entity-recognition-using","title":"Improving Large Language Models for Clinical Named Entity Recognition via Prompt Engineering","date":"2023-03-29","arxiv_id":"2303.16416","repositories_listed":1,"syntology":null},{"url":"/paper/hallucinations-in-large-multilingual","slug":"hallucinations-in-large-multilingual","title":"Hallucinations in Large Multilingual Translation Models","date":"2023-03-28","arxiv_id":"2303.16104","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/hallucinations-in-large-multilingual#ran","syntology_url":"https://syntology.ai/paper/2303.16104","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16104"}},"official":{"repos":["deep-spin/lmt_hallucinations"],"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/smartbook-ai-assisted-situation-report","slug":"smartbook-ai-assisted-situation-report","title":"SmartBook: AI-Assisted Situation Report Generation for Intelligence Analysts","date":"2023-03-25","arxiv_id":"2303.14337","repositories_listed":1,"syntology":null},{"url":"/paper/chatdoctor-a-medical-chat-model-fine-tuned-on","slug":"chatdoctor-a-medical-chat-model-fine-tuned-on","title":"ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledge","date":"2023-03-24","arxiv_id":"2303.14070","repositories_listed":1,"syntology":null},{"url":"/paper/chatgpt-for-programming-numerical-methods","slug":"chatgpt-for-programming-numerical-methods","title":"ChatGPT for Programming Numerical Methods","date":"2023-03-21","arxiv_id":"2303.12093","repositories_listed":1,"syntology":null},{"url":"/paper/language-model-behavior-a-comprehensive","slug":"language-model-behavior-a-comprehensive","title":"Language Model Behavior: A Comprehensive Survey","date":"2023-03-20","arxiv_id":"2303.11504","repositories_listed":1,"syntology":null},{"url":"/paper/is-prompt-all-you-need-no-a-comprehensive-and","slug":"is-prompt-all-you-need-no-a-comprehensive-and","title":"Large Language Model Instruction Following: A Survey of Progresses and Challenges","date":"2023-03-18","arxiv_id":"2303.10475","repositories_listed":1,"syntology":null},{"url":"/paper/can-ai-generated-text-be-reliably-detected","slug":"can-ai-generated-text-be-reliably-detected","title":"Can AI-Generated Text be Reliably Detected?","date":"2023-03-17","arxiv_id":"2303.11156","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-model-is-not-a-good-few-shot","slug":"large-language-model-is-not-a-good-few-shot","title":"Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!","date":"2023-03-15","arxiv_id":"2303.08559","repositories_listed":1,"syntology":null},{"url":"/paper/nl4opt-competition-formulating-optimization","slug":"nl4opt-competition-formulating-optimization","title":"NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions","date":"2023-03-14","arxiv_id":"2303.08233","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"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) · 1 unverified","sample_list":"/paper/nl4opt-competition-formulating-optimization#ran","syntology_url":"https://syntology.ai/paper/2303.08233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08233"}},"official":{"repos":["nl4opt/nl4opt-competition"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/high-throughput-generative-inference-of-large","slug":"high-throughput-generative-inference-of-large","title":"FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU","date":"2023-03-13","arxiv_id":"2303.06865","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/high-throughput-generative-inference-of-large#ran","syntology_url":"https://syntology.ai/paper/2303.06865","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.06865"}},"official":{"repos":["fminference/flexgen"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/prompting-large-language-models-with-answer","slug":"prompting-large-language-models-with-answer","title":"Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering","date":"2023-03-03","arxiv_id":"2303.01903","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_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","sample_list":"/paper/prompting-large-language-models-with-answer#ran","syntology_url":"https://syntology.ai/paper/2303.01903","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.01903"}},"official":{"repos":["milvlg/prophet"],"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"]}}},{"url":"/paper/language-is-not-all-you-need-aligning-1","slug":"language-is-not-all-you-need-aligning-1","title":"Language Is Not All You Need: Aligning Perception with Language Models","date":"2023-02-27","arxiv_id":"2302.14045","repositories_listed":1,"syntology":null},{"url":"/paper/reward-design-with-language-models","slug":"reward-design-with-language-models","title":"Reward Design with Language Models","date":"2023-02-27","arxiv_id":"2303.00001","repositories_listed":1,"syntology":null},{"url":"/paper/an-independent-evaluation-of-chatgpt-on","slug":"an-independent-evaluation-of-chatgpt-on","title":"An Independent Evaluation of ChatGPT on Mathematical Word Problems (MWP)","date":"2023-02-23","arxiv_id":"2302.13814","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/an-independent-evaluation-of-chatgpt-on#ran","syntology_url":"https://syntology.ai/paper/2302.13814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13814"}},"official":{"repos":["lab-v2/chatgpt_mwp_eval"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}}],"record_sha256":"f1f702598bc2048d57c79031949e1d07f42ee8b0e3c7a41ffeb208aa4eee764c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}