' that allows the reversal of operators. We demonstrate the elegance of the operators approach in a suitable programming language consisting of generic linear algebra operators such as Julia \\cite{bezanson2017julia}, and that it is possible to realize this abstraction in code. Our implementation shows how generic linear algebra can allow operators as elements of matrices, and without rewriting any code, the software carries through to completion giving the correct answer. ","authors":[{"id":"560286ad45cedb3395fc699c","name":"Alan Edelman"},{"id":"5628b7e045ce1e59660261f0","name":"Ekin Akyurek"},{"id":"542d3fe4dabfae12b980055a","name":"Yuyang Wang"}],"create_time":"2023-03-29T19:32:07.011Z","id":"6423ac6c90e50fcafd55c06f","num_citation":0,"pdf":"https:\u002F\u002Fcz5waila03cyo0tux1owpyofgoryroob.aminer.cn\u002FFE\u002F34\u002F9B\u002FFE349B268D3212D71089D926325B4C03.pdf","title":"BACKpropagation through BACK substitution with a BACKslash","urls":["db\u002Fjournals\u002Fcorr\u002Fcorr2303.html#abs-2303-15449","https:\u002F\u002Fdoi.org\u002F10.48550\u002FarXiv.2303.15449","https:\u002F\u002Farxiv.org\u002Fabs\u002F2303.15449"],"venue":{"info":{"name":"CoRR"},"volume":"abs\u002F2303.15449"},"versions":[{"id":"6423ac6c90e50fcafd55c06f","sid":"2303.15449","src":"arxiv","year":2023},{"id":"6456477dd68f896efae21b17","sid":"journals\u002Fcorr\u002Fabs-2303-15449","src":"dblp","year":2023}],"year":2023},{"abstract":" Despite their unprecedented success, even the largest language models make mistakes. Similar to how humans learn and improve using feedback, previous work proposed providing language models with natural language feedback to guide them in repairing their outputs. Because human-generated critiques are expensive to obtain, researchers have devised learned critique generators in lieu of human critics while assuming one can train downstream models to utilize generated feedback. However, this approach does not apply to black-box or limited access models such as ChatGPT, as they cannot be fine-tuned. Moreover, in the era of large general-purpose language agents, fine-tuning is neither computationally nor spatially efficient as it results in multiple copies of the network. In this work, we introduce RL4F (Reinforcement Learning for Feedback), a multi-agent collaborative framework where the critique generator is trained to maximize end-task performance of GPT-3, a fixed model more than 200 times its size. RL4F produces critiques that help GPT-3 revise its outputs. We study three datasets for action planning, summarization and alphabetization and show improvements (~5% on average) in multiple text similarity metrics over strong baselines across all three tasks. ","authors":[{"id":"64b916a016b3d9192137baa3","name":"Afra Feyza Akyürek"},{"id":"5628b7e045ce1e59660261f0","name":"Ekin Akyürek"},{"name":"Aman Madaan"},{"id":"63724c37ec88d95668cc9755","name":"Ashwin Kalyan"},{"id":"540561dddabfae8faa5ca7ee","name":"Peter Clark"},{"id":"5601bd5c45cedb3395eab6a6","name":"Derry Wijaya"},{"id":"53f48030dabfaec09f29ea31","name":"Niket Tandon"}],"create_time":"2023-05-16T04:58:21.706Z","hashs":{"h1":"rgnlf","h3":"rlrmo"},"id":"6462f13cd68f896efa911ee9","num_citation":0,"pages":{"end":"7733","start":"7716"},"pdf":"https:\u002F\u002Fcz5waila03cyo0tux1owpyofgoryroob.aminer.cn\u002FEC\u002F59\u002F48\u002FEC5948C9B9DC115DA06411A4603494FB.pdf","title":"RL4F: Generating Natural Language Feedback with Reinforcement Learning\n for Repairing Model Outputs","update_times":{"u_c_t":"2023-10-24T07:03:05.3Z"},"urls":["db\u002Fconf\u002Facl\u002Facl2023-1.html#AkyurekAKCWT23","https:\u002F\u002Faclanthology.org\u002F2023.acl-long.427","https:\u002F\u002Faclanthology.org\u002F2023.acl-long.427\u002F","db\u002Fjournals\u002Fcorr\u002Fcorr2305.html#abs-2305-08844","https:\u002F\u002Fdoi.org\u002F10.48550\u002FarXiv.2305.08844","https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.08844"],"venue":{"info":{"name":"conf_acl"},"volume":"abs\u002F2305.08844"},"venue_hhb_id":"5ea1afddedb6e7d53c00c104","versions":[{"id":"6462f13cd68f896efa911ee9","sid":"2305.08844","src":"arxiv","year":2023},{"id":"6479e3add68f896efa4e705b","sid":"journals\u002Fcorr\u002Fabs-2305-08844","src":"dblp","year":2023},{"id":"64ae66e53fda6d7f06849331","sid":"2023.acl-long.427","src":"conf_acl","year":2023},{"id":"64c78b9f3fda6d7f06db9a3d","sid":"conf\u002Facl\u002FAkyurekAKCWT23","src":"dblp","year":2023}],"year":2023},{"abstract":" Few-shot class incremental learning -- the problem of updating a trained classifier to discriminate among an expanded set of classes with limited labeled data -- is a key challenge for machine learning systems deployed in non-stationary environments. Existing approaches to the problem rely on complex model architectures and training procedures that are difficult to tune and re-use. In this paper, we present an extremely simple approach that enables the use of ordinary logistic regression classifiers for few-shot incremental learning. The key to this approach is a new family of subspace regularization schemes that encourage weight vectors for new classes to lie close to the subspace spanned by the weights of existing classes. When combined with pretrained convolutional feature extractors, logistic regression models trained with subspace regularization outperform specialized, state-of-the-art approaches to few-shot incremental image classification by up to 22% on the miniImageNet dataset. Because of its simplicity, subspace regularization can be straightforwardly extended to incorporate additional background information about the new classes (including class names and descriptions specified in natural language); these further improve accuracy by up to 2%. Our results show that simple geometric regularization of class representations offers an effective tool for continual learning. ","authors":[{"id":"64b916a016b3d9192137baa3","name":"Afra Feyza Akyürek"},{"id":"5628b7e045ce1e59660261f0","name":"Ekin Akyürek"},{"id":"5601bd5c45cedb3395eab6a6","name":"Derry Wijaya"},{"id":"53f42c2edabfaedf43504560","name":"Jacob Andreas"}],"citations":{"google_citation":6,"last_citation":5},"create_time":"2021-10-15T13:44:50.479Z","hashs":{"h1":"srfci","h3":"l"},"id":"6168f19c5244ab9dcbe2f90d","keywords":["few-shot class incremental learning","incremental learning","incremental classification","subspace regularization","manifold regularization","few-shot learning"],"lang":"en","num_citation":26,"pdf":"https:\u002F\u002Fcz5waila03cyo0tux1owpyofgoryroob.aminer.cn\u002F5A\u002F0D\u002F2F\u002F5A0D2FAED9EA1C13B25DB833F3481F95.pdf","pdf_src":["https:\u002F\u002Farxiv.org\u002Fpdf\u002F2110.07059","https:\u002F\u002Fopenreview.net\u002Fpdf\u002F8e50ad238e1d64a51be6a65f6da2e3606da02bef.pdf"],"title":"Subspace Regularizers for Few-Shot Class Incremental Learning","update_times":{"u_a_t":"2022-10-19T08:53:21.21Z","u_c_t":"2023-10-13T12:44:38.338Z","u_v_t":"2022-10-18T17:25:38.756Z"},"urls":["https:\u002F\u002Fdblp.org\u002Frec\u002Fconf\u002Ficlr\u002FAkyurekAWA22","https:\u002F\u002Fsemanticscholar.org\u002Fpaper\u002Ff8d77d2d33a86a02c7d2ddd3dcbb1dc48ccf265c","https:\u002F\u002Fopenreview.net\u002Fforum?id=boJy41J-tnQ","https:\u002F\u002Fsemanticscholar.org\u002Fpaper\u002F3a43859a9feecc53c0104d27c07577973c582f75","db\u002Fjournals\u002Fcorr\u002Fcorr2110.html#abs-2110-07059","https:\u002F\u002Farxiv.org\u002Fabs\u002F2110.07059"],"venue":{"info":{"name":"International Conference on Learning Representations (ICLR)","name_s":"ICLR"},"volume":"abs\u002F2110.07059"},"venue_hhb_id":"5ea1d518edb6e7d53c0100cb","versions":[{"id":"6168f19c5244ab9dcbe2f90d","sid":"2110.07059","src":"arxiv","year":2022},{"id":"6257c5a75aee126c0f467854","sid":"boJy41J-tnQ","src":"conf_iclr","vsid":"ICLR.cc\u002F2022\u002FConference","year":2022},{"id":"634d805190e50fcafd4dfa25","sid":"conf\u002Ficlr\u002FAkyurekAWA22","src":"dblp","vsid":"conf\u002Ficlr","year":2022},{"id":"61c8f9c05244ab9dcbd5f0c0","sid":"3a43859a9feecc53c0104d27c07577973c582f75","src":"semanticscholar"},{"id":"627ce0085aee126c0f5fe069","sid":"f8d77d2d33a86a02c7d2ddd3dcbb1dc48ccf265c","src":"semanticscholar"},{"id":"645647b8d68f896efae3cfda","sid":"journals\u002Fcorr\u002Fabs-2110-07059","src":"dblp","year":2021}],"year":2022},{"abstract":" Language models (LMs) have been shown to memorize a great deal of factual knowledge contained in their training data. But when an LM generates an assertion, it is often difficult to determine where it learned this information and whether it is true. In this paper, we propose the problem of fact tracing: identifying which training examples taught an LM to generate a particular factual assertion. Prior work on training data attribution (TDA) may offer effective tools for identifying such examples, known as \"proponents\". We present the first quantitative benchmark to evaluate this. We compare two popular families of TDA methods -- gradient-based and embedding-based -- and find that much headroom remains. For example, both methods have lower proponent-retrieval precision than an information retrieval baseline (BM25) that does not have access to the LM at all. We identify key challenges that may be necessary for further improvement such as overcoming the problem of gradient saturation, and also show how several nuanced implementation details of existing neural TDA methods can significantly improve overall fact tracing performance. ","authors":[{"id":"5628b7e045ce1e59660261f0","name":"Ekin Akyürek"},{"id":"562d24f045cedb3398d667b5","name":"Tolga Bolukbasi"},{"id":"562d26fa45cedb3398d6ac11","name":"Frederick Liu"},{"id":"652e6e7250dee4c4226dfeab","name":"Binbin Xiong"},{"name":"Ian Tenney"},{"id":"53f42c2edabfaedf43504560","name":"Jacob Andreas"},{"name":"Kelvin Guu"}],"create_time":"2022-05-24T13:48:36.958Z","hashs":{"h1":"tklmb","h3":"td"},"id":"628c4ce65aee126c0ff59f82","lang":"en","num_citation":0,"pdf":"https:\u002F\u002Fcz5waila03cyo0tux1owpyofgoryroob.aminer.cn\u002F98\u002F6B\u002F1D\u002F986B1D45873BF69E8B32A937B65FE616.pdf","pdf_src":["https:\u002F\u002Farxiv.org\u002Fpdf\u002F2205.11482"],"title":"Towards Tracing Factual Knowledge in Language Models Back to the\n Training Data","urls":["https:\u002F\u002Farxiv.org\u002Fabs\u002F2205.11482"],"versions":[{"id":"628c4ce65aee126c0ff59f82","sid":"2205.11482","src":"arxiv","year":2022}],"year":2022},{"abstract":" Humans can reason compositionally when presented with new tasks. Previous research shows that appropriate prompting techniques enable large language models (LLMs) to solve artificial compositional generalization tasks such as SCAN. In this work, we identify additional challenges in more realistic semantic parsing tasks with larger vocabulary and refine these prompting techniques to address them. Our best method is based on least-to-most prompting: it decomposes the problem using prompting-based syntactic parsing, then uses this decomposition to select appropriate exemplars and to sequentially generate the semantic parse. This method allows us to set a new state of the art for CFQ while requiring only 1% of the training data used by traditional approaches. Due to the general nature of our approach, we expect similar efforts will lead to new results in other tasks and domains, especially for knowledge-intensive applications. ","authors":[{"id":"63817fed18c6797fc6904d39","name":"Andrew Drozdov","org":"Department of Computer Science, University of Massachusetts, Amherst","orgid":"5f71b2951c455f439fe3cdb3","orgs":["Department of Computer Science, University of Massachusetts, Amherst"]},{"email":"schaerli@google.com","id":"53f4ce67dabfaeedd977bce2","name":"Nathanael Schärli"},{"id":"5628b7e045ce1e59660261f0","name":"Ekin Akyürek","org":"Massachusetts Institute of Technology","orgid":"62331e350a6eb147dca8a7ec","orgs":["Massachusetts Institute of Technology"]},{"id":"63738b639bb5705eda8b0cfc","name":"Nathan Scales","org":"Google","orgid":"5f71b2d21c455f439fe3e823","orgs":["Google"]},{"id":"53f42fd5dabfaee2a1c9b857","name":"Xinying Song","org":"Google","orgid":"5f71b2d21c455f439fe3e823","orgs":["Google"]},{"id":"542e4c9fdabfaed7c7c30ea1","name":"Xinyun Chen","org":"Google","orgid":"5f71b2d21c455f439fe3e823","orgs":["Google"]},{"id":"53f48de7dabfaea7cd1d4cd2","name":"Olivier Bousquet","org":"Google","orgid":"5f71b2d21c455f439fe3e823","orgs":["Google"]},{"id":"53f4334fdabfaedce550f474","name":"Denny Zhou","org":"Google Brain","orgid":"5f71b2d21c455f439fe3e823","orgs":["Google Brain"]}],"citations":{"google_citation":4,"last_citation":4},"create_time":"2022-09-30T04:53:54.919Z","hashs":{"h1":"cspll","h3":"m"},"id":"63365e7f90e50fcafd1a3626","keywords":["large language models","prompting","compositional generalization","natural language processing"],"lang":"en","num_citation":41,"pdf":"https:\u002F\u002Fcz5waila03cyo0tux1owpyofgoryroob.aminer.cn\u002FB4\u002FBB\u002F41\u002FB4BB41F0EF05FD25FDB942B665DA1C49.pdf","pdf_src":["https:\u002F\u002Farxiv.org\u002Fpdf\u002F2209.15003","https:\u002F\u002Fopenreview.net\u002Fpdf?id=gJW8hSGBys8","https:\u002F\u002Fopenreview.net\u002Fpdf\u002F668ef1e66f349e87c8948f0e5e5984608ebef31d.pdf"],"title":"Compositional Semantic Parsing with Large Language Models","update_times":{"u_a_t":"2022-10-01T08:23:40.258Z","u_c_t":"2023-11-03T07:27:06.715Z","u_v_t":"2023-04-11T03:03:15.404Z"},"urls":["db\u002Fconf\u002Ficlr\u002Ficlr2023.html#DrozdovSASSCBZ23","https:\u002F\u002Fopenreview.net\u002Fpdf?id=gJW8hSGBys8","https:\u002F\u002Farxiv.org\u002Fabs\u002F2209.15003","https:\u002F\u002Fopenreview.net\u002Fforum?id=gJW8hSGBys8"],"venue":{"info":{"name":"ICLR 2023"}},"versions":[{"id":"63365e7f90e50fcafd1a3626","sid":"2209.15003","src":"arxiv","year":2022},{"id":"63dcdb422c26941cf00b6451","sid":"gJW8hSGBys8","src":"conf_iclr","vsid":"ICLR.cc\u002F2023\u002FConference","year":2023},{"id":"6433f64790e50fcafd6ca384","sid":"2023#gJW8hSGBys8","src":"conf_iclr","vsid":"ICLR.cc\u002F2023\u002FConference","year":2023},{"id":"64a407ddd68f896efaf1cb82","sid":"conf\u002Ficlr\u002FDrozdovSASSCBZ23","src":"dblp","year":2023}],"year":2022}],"profilePubsTotal":5,"profilePatentsPage":0,"profilePatents":null,"profilePatentsTotal":null,"profilePatentsEnd":false,"profileProjectsPage":1,"profileProjects":{"success":true,"msg":"","data":null,"log_id":"2YvIdFlDOkP7XZDvbHW4upHFJ07"},"profileProjectsTotal":0,"newInfo":null,"checkDelPubs":[]}};