{"total":20,"papers":[{"id":"acl:2023.acl-demo.51","title":"A System for Answering Simple Questions in Multiple Languages","date":"2023-07-01","section":"Retrieval, embeddings, benchmarks","quality":-0.278672,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/ed9c84589f90bec427f8a82b8dfb446141afffabde9bb465aaac79038b809821/","source_url":"https://aclanthology.org/2023.acl-demo.51/","text_available":true},{"id":"arxiv:2402.12483","title":"Artifacts or Abduction: How Do LLMs Answer Multiple-Choice Questions Without the Question?","date":"2024-02-19","section":"Retrieval, embeddings, benchmarks","quality":-0.037184,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/1b9723010e10f9e91a6a9cc14c735ef6b1ff56c29c55c1204eeb18b6a43b7f15/","source_url":"https://arxiv.org/abs/2402.12483","text_available":true},{"id":"arxiv:2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","date":"2022-06-09","section":"Retrieval, embeddings, benchmarks","quality":0.491414,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/70882486c1f8c46cb7b26cf100847f770eb7b39b69dee56b8a21141141ef814d/","source_url":"https://arxiv.org/abs/2206.04615","text_available":true},{"id":"arxiv:2311.16452","title":"Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine","date":"2023-11-28","section":"Retrieval, embeddings, benchmarks","quality":0.058276,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/8e8303d0328f412b165c8cdfca91debf742ea45ed7865a0d96ee3905e5bba919/","source_url":"https://arxiv.org/abs/2311.16452","text_available":true},{"id":"arxiv:2606.18543","title":"CEO-Bench: Can Agents Play the Long Game?","date":"2026-06-16","section":"Retrieval, embeddings, benchmarks","quality":0.174568,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/696d7ac1dfd7539fbe8147ed713574b8eb5a7400a35e96805c7f0c9add99165c/","source_url":"https://arxiv.org/abs/2606.18543","text_available":true},{"id":"arxiv:2212.14024","title":"Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP","date":"2022-12-28","section":"Retrieval, embeddings, benchmarks","quality":0.294453,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/09c4c9bae4e016c9ce276cf84a46742b5b21168f4181202b35c207baf887f71e/","source_url":"https://arxiv.org/abs/2212.14024","text_available":true},{"id":"arxiv:2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","date":"2021-01-06","section":"Retrieval, embeddings, benchmarks","quality":0.058238,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/5b44455f95aaaeefc838faceeaf20aaf1008889ca2e479d95291e245d5365a36/","source_url":"https://arxiv.org/abs/2101.02235","text_available":true},{"id":"arxiv:2112.07899","title":"Large Dual Encoders Are Generalizable Retrievers","date":"2021-12-15","section":"Retrieval, embeddings, benchmarks","quality":0.297587,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a98e608b4e34094fed75a118c0663f5f02f485081981cecc2bf3350181d61a51/","source_url":"https://arxiv.org/abs/2112.07899","text_available":true},{"id":"arxiv:2304.08467","title":"Learning to Compress Prompts with Gist Tokens","date":"2023-04-17","section":"Retrieval, embeddings, benchmarks","quality":-0.070542,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e77a0eef338c287982221a4a4770c18f85eb99a6d245af931d60a6ec9190ba69/","source_url":"https://arxiv.org/abs/2304.08467","text_available":true},{"id":"arxiv:2205.13147","title":"Matryoshka Representation Learning","date":"2022-05-26","section":"Retrieval, embeddings, benchmarks","quality":0.591178,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/803baa0a8ea7ba1bc63bee0ce80006bf4f403ca0db16ada95dd8198da9a4a899/","source_url":"https://arxiv.org/abs/2205.13147","text_available":true},{"id":"arxiv:2410.07095","title":"MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering","date":"2024-10-09","section":"Retrieval, embeddings, benchmarks","quality":0.31646,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/f0a0c6321ec079098a36ad19b3900d77197a3af1f6bbf6eee8a083e5eb03d42e/","source_url":"https://arxiv.org/abs/2410.07095","text_available":true},{"id":"arxiv:2212.09741","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","date":"2022-12-19","section":"Retrieval, embeddings, benchmarks","quality":0.51946,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/b162d4a59ad6b25fd180e566615cf3dc2cd3a6c505f0421e15fd036236ad2ecd/","source_url":"https://arxiv.org/abs/2212.09741","text_available":true},{"id":"url:lilianweng.github.io/posts/2020-10-29-odqa","title":"Open Domain Question Answering (Lilian Weng)","date":"2020-10-29","section":"Retrieval, embeddings, benchmarks","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e1d9834a1aa6585269d7d2a8ec6f3db4dc87d14412778360bc484b06c4486bc3/","source_url":"https://lilianweng.github.io/posts/2020-10-29-odqa/","text_available":false},{"id":"arxiv:2405.08007","title":"People cannot distinguish GPT-4 from a human in a Turing test","date":"2024-05-09","section":"Retrieval, embeddings, benchmarks","quality":-0.265154,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/ec6cede2a895468a1dd14c92111b2a895f42c9eaab66f94918ef5340d1b183e1/","source_url":"https://arxiv.org/abs/2405.08007","text_available":true},{"id":"acl:2022.acl-long.360","title":"PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization","date":"2021-10-16","section":"Retrieval, embeddings, benchmarks","quality":-0.070728,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/7ea72ee4d97ca9c2839284c71ef41df5bb2db7ca0ab28e219c275e13139eaace/","source_url":"https://aclanthology.org/2022.acl-long.360/","text_available":true},{"id":"arxiv:2309.16797","title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","date":"2023-09-28","section":"Retrieval, embeddings, benchmarks","quality":-0.189598,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/daac3bcfcd7f39084d995905e9ef96ae01c5aab7bfe8e565bd7622b4e44088f7/","source_url":"https://arxiv.org/abs/2309.16797","text_available":true},{"id":"arxiv:2402.16822","title":"Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts","date":"2024-02-26","section":"Retrieval, embeddings, benchmarks","quality":0.383425,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/d4803e891a4b9c929eca007e3c3f003c330d2fc741109975c6ddd7d2c32828fc/","source_url":"https://arxiv.org/abs/2402.16822","text_available":true},{"id":"url:selfrag.github.io","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","date":"2023-10-17","section":"Retrieval, embeddings, benchmarks","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/f2a6b92a158b280a6699d4fda0ed474777be788abf9ed561ab7d61da1da57ad1/","source_url":"https://selfrag.github.io/","text_available":false},{"id":"arxiv:2403.07714","title":"StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models","date":"2024-03-12","section":"Retrieval, embeddings, benchmarks","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/ed03ae4fed851402f7c4c5378410fc34374148218bc20e4e7e92522063d06df9/","source_url":"https://arxiv.org/abs/2403.07714","text_available":true},{"id":"acl:2022.emnlp-main.340","title":"Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks","date":"2022-04-16","section":"Retrieval, embeddings, benchmarks","quality":0.101373,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e43a06571b7e8d89abd5f20f8f520c8bc3d3eb32ffb156cb7fc9e0469fc14b0a/","source_url":"https://aclanthology.org/2022.emnlp-main.340/","text_available":true}],"next":null}