Papers of 2023 — page 4502 papers · all years1 2 3 4 5 6MMBench: Is Your Multi-modal Model an All-around Player?Yuan Liu, Haodong Duan, Yuanhan Zhang, et al.arXiv:2307.06281MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language ModelsChaoyou Fu, Peixian Chen, Yunhang Shen, et al.arXiv:2306.13394MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIXiang Yue, Yuansheng Ni, Kai Zhang, et al.arXiv:2311.16502Model Tells You What to Discard: Adaptive KV Cache Compression for LLMsSuyu Ge, Yunan Zhang, Liyuan Liu, et al.arXiv:2310.01801Morphological Inflection: A Reality CheckJordan Kodner, Sarah Payne, Salam Khalifa, et al.EnglishmPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality CollaborationQinghao Ye, Haiyang Xu, Jiabo Ye, et al.arXiv:2311.04257mPLUG-Owl: Modularization Empowers Large Language Models with MultimodalityQinghao Ye, Haiyang Xu, Guohai Xu, et al.arXiv:2304.14178Multi-step Jailbreaking Privacy Attacks on ChatGPTHaoran Li, Dadi Guo, Wei Fan, et al.Findings of the Association for Computational…Multi-VALUE: A Framework for Cross-Dialectal English NLPCaleb Ziems, William Held, Jingfeng Yang, et al.EnglishMultilingual Jailbreak Challenges in Large Language ModelsYue Deng, Wenxuan Zhang, Sinno Jialin Pan, et al.arXiv:2310.06474Multilingual Sequence-to-Sequence Models for Hebrew NLPMatan Eyal, Hila Noga, Roee Aharoni, et al.Modern HebrewMultimodal Chain-of-Thought Reasoning in Language ModelsZhuosheng Zhang, Aston Zhang, Mu Li, et al.arXiv:2302.00923MVBench: A Comprehensive Multi-modal Video Understanding BenchmarkKunchang Li, Yali Wang, Yinan He, et al.arXiv:2311.17005Neural Codec Language Models are Zero-Shot Text to Speech SynthesizersChengyi Wang, Sanyuan Chen, Yu Wu, et al.arXiv:2301.02111NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each BenchmarkOscar Sainz, Jon Campos, Iker García-Ferrero, et al.Findings of the Association for Computational…Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought PromptingHaoyang Huang, Tianyi Tang, Dongdong Zhang, et al.arXiv:2305.07004Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt InjectionKai Greshake, Sahar Abdelnabi, Shailesh Mishra, et al.arXiv:2302.12173Nothing New Under the Sun? The Study of Biblical Hebrew in the Era of Generative Pre-trained AIA. G. ElrodAncient HebrewNâbra: Syrian Arabic Dialects with Morphological AnnotationsAmal Nayouf, Tymaa Hammouda, Mustafa Jarrar, et al.Semitic languagesOBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text DocumentsHugo Lauren\ccon, Lucile Saulnier, Leo Tronchon, et al.arXiv:2306.16527OCRBench: On the Hidden Mystery of OCR in Large Multimodal ModelsYuliang Liu, Zhang Li, Mingxin Huang, et al.arXiv:2305.07895Offensive Hebrew Corpus and Detection using BERTNagham Hamad, Mustafa Jarrar, Mohammad Khalilia, et al.Modern HebrewOkapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human FeedbackViet Lai, Chien Nguyen, Nghia Ngo, et al.Proceedings of the 2023 Conference on Empirical…OmniQuant: Omnidirectionally Calibrated Quantization for Large Language ModelsWenqi Shao, Mengzhao Chen, Zhaoyang Zhang, et al.arXiv:2308.13137On Old English swa 'so'Sigrid BeckEnglishOn Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot ReasoningOmar Shaikh, Hongxin Zhang, William Held, et al.Proceedings of the 61st Annual Meeting of the…On-Policy Distillation of Language Models: Learning from Self-Generated MistakesRishabh Agarwal, Nino Vieillard, Yongchao Zhou, et al.arXiv:2306.13649Open-source Frame Semantic ParsingDavid ChaninEnglishOpenAssistant Conversations -- Democratizing Large Language Model AlignmentAndreas Köpf, Yannic Kilcher, Dimitri von Rütte, et al.arXiv:2304.07327OpenChat: Advancing Open-source Language Models with Mixed-Quality DataGuan Wang, Sijie Cheng, Xianyuan Zhan, et al.arXiv:2309.11235OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language ModelsAnas Awadalla, Irena Gao, Josh Gardner, et al.arXiv:2308.01390OpenWebMath: An Open Dataset of High-Quality Mathematical Web TextKeiran Paster, Marco Dos Santos, Zhangir Azerbayev, et al.arXiv:2310.06786Optimizing the Neural Network Training for OCR Error Correction of Historical Hebrew TextsOmri Suissa, Avshalom Elmalech, Maayan Zhitomirsky-GeffetAncient HebrewOrca 2: Teaching Small Language Models How to ReasonArindam Mitra, Luciano Del Corro, Shweti Mahajan, et al.arXiv:2311.11045Orca: Progressive Learning from Complex Explanation Traces of GPT-4Subhabrata Mukherjee, Arindam Mitra, Ganesh Jawahar, et al.arXiv:2306.02707Otter: A Multi-Modal Model with In-Context Instruction TuningBo Li, Yuanhan Zhang, Liangyu Chen, et al.arXiv:2305.03726PaLM 2 Technical ReportRohan Anil, Andrew M. Dai, Orhan Firat, et al.arXiv:2305.10403PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning OptimizationYidong Wang, Zhuohao Yu, Zhengran Zeng, et al.arXiv:2306.05087ParaAMR: A Large-Scale Syntactically Diverse Paraphrase Dataset by AMR Back-TranslationKuan-Hao Huang, Varun Iyer, I-Hung Hsu, et al.Machine translationParameter-efficient fine-tuning of large-scale pre-trained language modelsNing Ding, Yujia Qin, Guang You Yang, et al.Nature Machine IntelligenceParaphrasing evades detectors of AI-generated text, but retrieval is an effective defenseKalpesh Krishna, Yixiao Song, Marzena Karpinska, et al.arXiv:2303.13408Personality Traits in Large Language ModelsGreg Serapio-Garcia, Mustafa Safdari, Clement Crepy, et al.arXiv:2307.00184Physics of Language Models: Part 3.1, Knowledge Storage and ExtractionZeyuan Allen-Zhu, Yuanzhi LiarXiv:2309.14316PragmatiCQA: A Dataset for Pragmatic Question Answering in ConversationsPeng Qi, Nina Du, Christopher Manning, et al.EnglishPreference Ranking Optimization for Human AlignmentFeifan Song, Bowen Yu, Minghao Li, et al.arXiv:2306.17492PreWoMe: Exploiting Presuppositions as Working Memory for Long Form Question AnsweringWookje Han, Jinsol Park, Kyungjae LeeEnglishPrinciple-Driven Self-Alignment of Language Models from Scratch with Minimal Human SupervisionZhiqing Sun, Yikang Shen, Qinhong Zhou, et al.arXiv:2305.03047Progress measures for grokking via mechanistic interpretabilityNeel Nanda, Lawrence Chan, Tom Lieberum, et al.arXiv:2301.05217Prometheus: Inducing Fine-grained Evaluation Capability in Language ModelsSeungone Kim, Jamin Shin, Yejin Cho, et al.arXiv:2310.08491Prompt Injection attack against LLM-integrated ApplicationsYi Liu; Gelei Deng; Yuekang Li; Kailong Wang; Zihao Wang; Xiaofeng Wang; Tianwei Zhang; Yepang Liu; Haoyu Wang; Yan Zheng; Leo Yu Zhang;, Yang LiuarXiv:2306.05499Promptbreeder: Self-Referential Self-Improvement Via Prompt EvolutionChrisantha Fernando, Dylan Banarse, Henryk Michalewski, et al.arXiv:2309.16797Prompting Large Language Model for Machine Translation: A Case StudyBiao Zhang, Barry Haddow, Alexandra BircharXiv:2301.07069PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial PromptsKaijie Zhu, Jindong Wang, Jiaheng Zhou, et al.arXiv:2306.04528ProofNet: Autoformalizing and Formally Proving Undergraduate-Level MathematicsZhangir Azerbayev, Bartosz Piotrowski, Hailey Schoelkopf, et al.arXiv:2302.12433QUDeval: The Evaluation of Questions Under Discussion Discourse ParsingYating Wu, Ritika Mangla, Greg Durrett, et al.EnglishQuery Rewriting in Retrieval-Augmented Large Language ModelsXinbei Ma, Yeyun Gong, Pengcheng He, et al.Proceedings of the 2023 Conference on Empirical…Query2doc: Query Expansion with Large Language ModelsLiang Wang, Nan Yang, Furu WeiProceedings of the 2023 Conference on Empirical…Qwen Technical ReportJinze Bai, Shuai Bai, Yunfei Chu, et al.arXiv:2309.16609Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language ModelsYunfei Chu, Jin Xu, Xiaohuan Zhou, et al.arXiv:2311.07919Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and BeyondJinze Bai, Shuai Bai, Shusheng Yang, et al.arXiv:2308.12966RA-DIT: Retrieval-Augmented Dual Instruction TuningXi Victoria Lin, Xilun Chen, Mingda Chen, et al.arXiv:2310.01352RAFT: Reward rAnked FineTuning for Generative Foundation Model AlignmentHanze Dong, Wei Xiong, Deepanshu Goyal, et al.arXiv:2304.06767Ragas: Automated Evaluation of Retrieval Augmented GenerationShahul Es, Jithin James, Luis Espinosa-Anke, et al.arXiv:2309.15217RARR: Researching and Revising What Language Models Say, Using Language ModelsLuyu Gao, Zhuyun Dai, Panupong Pasupat, et al.Proceedings of the 61st Annual Meeting of the…Rediscovered Fragments Shed New Light on a Proto-Masoretic Torah ScrollPaul SandersAncient HebrewREFINER: Reasoning Feedback on Intermediate RepresentationsDebjit Paul, Mete Ismayilzada, Maxime Peyrard, et al.arXiv:2304.01904Reflexion: Language Agents with Verbal Reinforcement LearningNoah Shinn, Federico Cassano, Edward Berman, et al.arXiv:2303.11366Reinforced Self-Training (ReST) for Language ModelingCaglar Gulcehre, Tom Le Paine, Srivatsan Srinivasan, et al.arXiv:2308.08998REPLUG: Retrieval-Augmented Black-Box Language ModelsWeijia Shi, Sewon Min, Michihiro Yasunaga, et al.arXiv:2301.12652Representation Engineering: A Top-Down Approach to AI TransparencyAndy Zou, Long Phan, Sarah Chen, et al.arXiv:2310.01405Results of WMT23 Metrics Shared Task: Metrics Might Be Guilty but References Are Not InnocentMarkus Freitag, Nitika Mathur, Chi-kiu Lo, et al.Proceedings of the Eighth Conference on Machine…Rethinking Benchmark and Contamination for Language Models with Rephrased SamplesShuo Yang, Wei-Lin Chiang, Lianmin Zheng, et al.arXiv:2311.04850Retrieval meets Long Context Large Language ModelsPeng Xu, Wei Ping, Xianchao Wu, et al.arXiv:2310.03025Retrieval-Augmented Generation for Large Language Models: A SurveyYunfan Gao, Yun Xiong, Xinyu Gao, et al.arXiv:2312.10997Ring Attention with Blockwise Transformers for Near-Infinite ContextHao Liu, Matei Zaharia, Pieter AbbeelarXiv:2310.01889Role-Play with Large Language ModelsMurray Shanahan, Kyle McDonell, Laria ReynoldsarXiv:2305.16367RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language ModelsZekun Moore Wang, Zhongyuan Peng, Haoran Que, et al.arXiv:2310.00746RRHF: Rank Responses to Align Language Models with Human Feedback without tearsZheng Yuan, Hongyi Yuan, Chuanqi Tan, et al.arXiv:2304.05302Safe RLHF: Safe Reinforcement Learning from Human FeedbackJosef Dai, Xuehai Pan, Ruiyang Sun, et al.arXiv:2310.12773Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow InstructionsFederico Bianchi, Mirac Suzgun, Giuseppe Attanasio, et al.arXiv:2309.07875SafetyBench: Evaluating the Safety of Large Language ModelsZhexin Zhang, Leqi Lei, Lindong Wu, et al.arXiv:2309.07045SALMONN: Towards Generic Hearing Abilities for Large Language ModelsChangli Tang, Wenyi Yu, Guangzhi Sun, et al.arXiv:2310.13289SantaCoder: don't reach for the stars!Loubna Ben Allal, Raymond Li, Denis Kocetkov, et al.arXiv:2301.03988Scalable Extraction of Training Data from (Production) Language ModelsMilad Nasr, Nicholas Carlini, Jonathan Hayase, et al.arXiv:2311.17035Scaling Relationship on Learning Mathematical Reasoning with Large Language ModelsZheng Yuan, Hongyi Yuan, Chengpeng Li, et al.arXiv:2308.01825Scaling Speech Technology to 1,000+ LanguagesVineel Pratap, Andros Tjandra, Bowen Shi, et al.arXiv:2305.13516Scaling up CometKiwi: Unbabel-IST 2023 Submission for the Quality Estimation Shared TaskRicardo Rei, Nuno M. Guerreiro, José Pombal, et al.Proceedings of the Eighth Conference on Machine…SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language ModelsXiaoxuan Wang, Ziniu Hu, Pan Lu, et al.arXiv:2307.10635Scoring Coreference Chains with Split-Antecedent AnaphorsSilviu Paun, Juntao Yu, Nafise Sadat Moosavi, et al.EnglishSCOTT: Self-Consistent Chain-of-Thought DistillationPeifeng Wang, Zhengyang Wang, Zheng Li, et al.Proceedings of the 61st Annual Meeting of the…SDXL: Improving Latent Diffusion Models for High-Resolution Image SynthesisDustin Podell, Zion English, Kyle Lacey, et al.arXiv:2307.01952Seamless: Multilingual Expressive and Streaming Speech TranslationSeamless Communication, Loic Barrault, Yu-An Chung, et al.arXiv:2312.05187SeamlessM4T: Massively Multilingual & Multimodal Machine TranslationSeamless Communication, Loic Barrault, Yu-An Chung, et al.arXiv:2308.11596Secrets of RLHF in Large Language Models Part I: PPORui Zheng, Shihan Dou, Songyang Gao, et al.arXiv:2307.04964SEED-Bench: Benchmarking Multimodal LLMs with Generative ComprehensionBohao Li, Rui Wang, Guangzhi Wang, et al.arXiv:2307.16125Segment AnythingAlexander Kirillov, Eric Mintun, Nikhila Ravi, et al.arXiv:2304.02643Self-Alignment with Instruction BacktranslationXian Li, Ping Yu, Chunting Zhou, et al.arXiv:2308.06259Self-Evaluation Guided Beam Search for ReasoningYuxi Xie, Kenji Kawaguchi, Yiran Zhao, et al.arXiv:2305.00633Self-RAG: Learning to Retrieve, Generate, and Critique through Self-ReflectionAkari Asai, Zeqiu Wu, Yizhong Wang, et al.arXiv:2310.11511Sentiment Analysis in the Era of Large Language Models: A Reality CheckWenxuan Zhang, Yue Deng, Bing Liu, et al.arXiv:2305.150051 2 3 4 5 6