Papers of 2024 — page 1276 papers · all years1 2 3$\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World DomainsShunyu Yao, Noah Shinn, Pedram Razavi, et al.arXiv:2406.12045A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language ModelsS.M Towhidul Islam Tonmoy, S M Mehedi Zaman, Vinija Jain, et al.arXiv:2401.01313A Dataset for Metaphor Detection in Early Medieval Hebrew PoetryMichael Toker, Oren Mishali, Ophir Münz-Manor, et al.Ancient HebrewA First Look at the Ugaritic Poetic Text CorpusTillmann Dönicke, Clemens Steinberger, Max-Ferdinand Zeterberg, et al.Ancient HebrewA Language Modeling Approach to Diacritic-Free Hebrew TTSAmit Roth, Arnon Turetzky, Yossi AdiModern HebrewA Language-agnostic Model of Child Language AcquisitionLouis Mahon, Omri Abend, Uri Berger, et al.Modern HebrewA Roadmap to Pluralistic AlignmentTaylor Sorensen, Jared Moore, Jillian Fisher, et al.arXiv:2402.05070A Survey on Large Language Models for Code GenerationJuyong Jiang, Fan Wang, Jiasi Shen, et al.arXiv:2406.00515A Survey on Model Compression for Large Language ModelsXunyu Zhu, Jian Li, Yong Liu, et al.Transactions of the Association for…A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language ModelsWenqi Fan; Yujuan Ding; Liangbo Ning; Shijie Wang; Hengyun Li; Dawei Yin; Tat-Seng Chua;, Qing LiarXiv:2405.06211A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and ApplicationsPranab Sahoo; Ayush Kumar Singh; Sriparna Saha; Vinija Jain; Samrat Mondal;, Aman ChadhaarXiv:2402.07927A Truly Joint Neural Architecture for Segmentation and ParsingDanit Yshaayahu Levi, Reut TsarfatyModern HebrewAdapting LLMs to Hebrew: Unveiling DictaLM 2.0 with Enhanced Vocabulary and Instruction CapabilitiesShaltiel Shmidman, Avi Shmidman, Amir DN Cohen, et al.Modern HebrewAdaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question ComplexitySoyeong Jeong, Jinheon Baek, Sukmin Cho, et al.Proceedings of the 2024 Conference of the North…AGIEval: A Human-Centric Benchmark for Evaluating Foundation ModelsWanjun Zhong, Ruixiang Cui, Yiduo Guo, et al.Findings of the Association for Computational…Allen Institute for AI @ SIGTYP 2024 Shared Task on Word Embedding Evaluation for Ancient and Historical LanguagesLester James V. MirandaAncient HebrewAlphaMath Almost Zero: Process Supervision without ProcessGuoxin Chen, Minpeng Liao, Chengxi Li, et al.arXiv:2405.03553An Empirical Study on Vague Deictic Temporal AdverbialsSvenja Kenneweg, Brendan Balcerak Jackson, Joerg Deigmoeller, et al.EnglishAn Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language ModelsLiang Chen, Haozhe Zhao, Tianyu Liu, et al.arXiv:2403.06764Ancient but Digitized: Developing Handwritten Optical Character Recognition for East Syriac Script Through Creating KHAMIS DatasetAmeer Majeed, Hossein HassaniAramaicAnnotation Scheme for English Argument Structure Constructions TreebankHakyung Sung, Kristopher KyleEnglishArabic Diacritization Using Morphologically Informed Character-Level ModelMuhammad Morsy Elmallah, Mahmoud Reda, Kareem Darwish, et al.Semitic languagesArabicMMLU: Assessing Massive Multitask Language Understanding in ArabicFajri Koto, Haonan Li, Sara Shatnawi, et al.Findings of the Association for Computational…Are LLMs Breaking MT Metrics? Results of the WMT24 Metrics Shared TaskMarkus Freitag, Nitika Mathur, Daniel Deutsch, et al.Proceedings of the Ninth Conference on Machine…Are We on the Right Way for Evaluating Large Vision-Language Models?Lin Chen, Jinsong Li, Xiaoyi Dong, et al.arXiv:2403.20330Assessing the Cross-linguistic Utility of Abstract Meaning RepresentationShira Wein, Nathan SchneiderMachine translationAt the Crossroad of Cuneiform and NLP: Challenges for Fine-grained Part-of-speech TaggingGustav Ryberg Smidt, Els Lefever, Katrien de GraefSemitic languagesAya 23: Open Weight Releases to Further Multilingual ProgressViraat Aryabumi, John Dang, Dwarak Talupuru, et al.arXiv:2405.15032Aya Dataset: An Open-Access Collection for Multilingual Instruction TuningShivalika Singh, Freddie Vargus, Daniel D'souza, et al.Proceedings of the 62nd Annual Meeting of the…Aya Expanse: Combining Research Breakthroughs for a New Multilingual FrontierJohn Dang, Shivalika Singh, Daniel D'souza, et al.arXiv:2412.04261Aya Model: An Instruction Finetuned Open-Access Multilingual Language ModelAhmet Üstün, Viraat Aryabumi, Zheng-Xin Yong, et al.arXiv:2402.07827Benchmarking Large Language Models for News SummarizationTianyi Zhang, Faisal Ladhak, Esin Durmus, et al.Transactions of the Association for…Benchmarking Retrieval-Augmented Generation for MedicineGuangzhi Xiong, Qiao Jin, Zhiyong Lu, et al.Findings of the Association for Computational…Beyond Correlation: Interpretable Evaluation of Machine Translation MetricsStefano Perrella, Lorenzo Proietti, Pere-Lluís Huguet Cabot, et al.Machine translationBeyond Orthography: Automatic Recovery of Short Vowels and Dialectal Sounds in ArabicYassine El Kheir, Hamdy Mubarak, Ahmed Ali, et al.Semitic languagesBigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex InstructionsTerry Yue Zhuo, Minh Chien Vu, Jenny Chim, et al.arXiv:2406.15877BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical DomainsYanis Labrak, Adrien Bazoge, Emmanuel Morin, et al.Findings of the Association for Computational…BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and LanguagesJunho Myung, Nayeon Lee, Yi Zhou, et al.arXiv:2406.09948Break the Sequential Dependency of LLM Inference Using Lookahead DecodingYichao Fu, Peter Bailis, Ion Stoica, et al.arXiv:2402.02057Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMsShengbang Tong, Ellis Brown, Penghao Wu, et al.arXiv:2406.16860Camel Morph MSA: A Large-Scale Open-Source Morphological Analyzer for Modern Standard ArabicChristian Khairallah, Salam Khalifa, Reham Marzouk, et al.Semitic languagesCan LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP ResearchersChenglei Si, Diyi Yang, Tatsunori HashimotoarXiv:2409.04109Can Your Model Tell a Negation from an Implicature? Unravelling Challenges With Intent EncodersYuwei Zhang, Siffi Singh, Sailik Sengupta, et al.EnglishCBR-RAG: Case-Based Reasoning for Retrieval Augmented Generation in LLMs for Legal Question AnsweringNirmalie Wiratunga, Ramitha Abeyratne, Lasal Jayawardena, et al.arXiv:2404.04302Challenges to Evaluating the Generalization of Coreference Resolution Models: A Measurement Modeling PerspectiveIan Porada, Alexandra Olteanu, Kaheer Suleman, et al.EnglishChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All ToolsTeam GLM, Aohan Zeng, Bin Xu, et al.arXiv:2406.12793Code Llama: Open Foundation Models for CodeBaptiste Rozière, Jonas Gehring, Fabian Gloeckle, et al.arXiv:2308.12950Code-Switching and Back-Transliteration Using a Bilingual ModelDaniel Weisberg Mitelman, Nachum Dershowitz, Kfir BarAramaicCogVideoX: Text-to-Video Diffusion Models with An Expert TransformerZhuoyi Yang, Jiayan Teng, Wendi Zheng, et al.arXiv:2408.06072COMICORDA: Dialogue Act Recognition in Comic BooksJiri Martinek, Pavel Kral, Ladislav Lenc, et al.EnglishComputational Methods for the Analysis of Complementizer Variability in Language and Literature: The Case of Hebrew "she-" and "ki"Avi Shmidman, Aynat RubinsteinAncient HebrewComputational Morphology and Lexicography Modeling of Modern Standard Arabic NominalsChristian Khairallah, Reham Marzouk, Salam Khalifa, et al.Semitic languagesContinual Pre-Training for Cross-Lingual LLM Adaptation: Enhancing Japanese Language CapabilitiesKazuki Fujii, Taishi Nakamura, Mengsay Loem, et al.arXiv:2404.17790Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine TranslationHaoran Xu, Amr Sharaf, Yunmo Chen, et al.arXiv:2401.08417Corrective Retrieval Augmented GenerationShi-Qi Yan, Jia-Chen Gu, Yun Zhu, et al.arXiv:2401.15884Critical biblical studies via word frequency analysis: unveiling text authorshipShira Faigenbaum-Golovin, Alon Kipnis, Axel Buhler, et al.Ancient HebrewCRUXEval: A Benchmark for Code Reasoning, Understanding and ExecutionAlex Gu, Baptiste Rozière, Hugh Leather, et al.arXiv:2401.03065CultureLLM: Incorporating Cultural Differences into Large Language ModelsCheng Li, Mengzhou Chen, Jindong Wang, et al.arXiv:2402.10946Cutting Through the Noise: Boosting LLM Performance on Math Word ProblemsUjjwala Anantheswaran, Himanshu Gupta, Kevin Scaria, et al.Mova's core listD-Nikud: Enhancing Hebrew Diacritization with LSTM and Pretrained ModelsAdi Rosenthal, Nadav ShakedAncient HebrewDataComp-LM: In search of the next generation of training sets for language modelsJeffrey Li, Alex Fang, Georgios Smyrnis, et al.arXiv:2406.11794Dating ancient manuscripts using radiocarbon and AI-based writing style analysisMladen Popovic, Maruf A. Dhali, Lambert Schomaker, et al.Ancient HebrewDeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code IntelligenceDeepSeek-AI, Qihao Zhu, Daya Guo, et al.arXiv:2406.11931DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree SearchHuajian Xin, Z. Z. Ren, Junxiao Song, et al.arXiv:2408.08152DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic DataHuajian Xin, Daya Guo, Zhihong Shao, et al.arXiv:2405.14333DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal UnderstandingZhiyu Wu, Xiaokang Chen, Zizheng Pan, et al.arXiv:2412.10302DeepSeek-VL: Towards Real-World Vision-Language UnderstandingHaoyu Lu, Wen Liu, Bo Zhang, et al.arXiv:2403.05525DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language ModelsZhihong Shao, Peiyi Wang, Qihao Zhu, et al.arXiv:2402.03300Detecting Narrative Patterns in Biblical Hebrew and GreekHope McGovern, Hale Sirin, Tom Lippincott, et al.Ancient HebrewDistiLLM: Towards Streamlined Distillation for Large Language ModelsJongwoo Ko, Sungnyun Kim, Tianyi Chen, et al.arXiv:2402.03898Do Llamas Work in English? On the Latent Language of Multilingual TransformersChris Wendler, Veniamin Veselovsky, Giovanni Monea, et al.Proceedings of the 62nd Annual Meeting of the…Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMsXingyu Chen, Jiahao Xu, Tian Liang, et al.arXiv:2412.21187EAGLE: Speculative Sampling Requires Rethinking Feature UncertaintyYuhui Li, Fangyun Wei, Chao Zhang, et al.arXiv:2401.15077Embible: Reconstruction of Ancient Hebrew and Aramaic Texts Using TransformersNiv Fono, Harel Moshayof, Eldar Karol, et al.Ancient HebrewEnhancing TTS Stability in Hebrew using Discrete Semantic UnitsElla Zeldes, Or Tal, Yossi AdiModern HebrewError Span Annotation: A Balanced Approach for Human Evaluation of Machine TranslationTom Kocmi, Vilém Zouhar, Eleftherios Avramidis, et al.Proceedings of the Ninth Conference on Machine…EtymoLink: A Structured English Etymology DatasetYuan Gao, Weiwei SunEnglishEuroLLM: Multilingual Language Models for EuropePedro Henrique Martins, Patrick Fernandes, Joao Alves, et al.arXiv:2409.16235Evaluating large language models for the tasks of PoS tagging within the Universal Dependency frameworkMateus Machado, Evandro RuizMova's core listExecutable Code Actions Elicit Better LLM AgentsXingyao Wang, Yangyi Chen, Lifan Yuan, et al.arXiv:2402.01030Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time ScalingZhe Chen, Weiyun Wang, Yue Cao, et al.arXiv:2412.05271Exploring Human-Like Translation Strategy with Large Language ModelsZhiwei He, Tian Liang, Wenxiang Jiao, et al.Transactions of the Association for…Exploring Tokenization Strategies and Vocabulary Sizes for Enhanced Arabic Language ModelsMohamed Taher Alrefaie, Nour Eldin Morsy, Nada SamirSemitic languagesEyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMsShengbang Tong, Zhuang Liu, Yuexiang Zhai, et al.arXiv:2401.06209Findings of the WMT24 General Machine Translation Shared Task: The LLM Era Is Here but MT Is Not Solved YetTom Kocmi, Eleftherios Avramidis, Rachel Bawden, et al.Proceedings of the Ninth Conference on Machine…Fitting Fixed Expressions into the UD Mould: Swedish as a Use CaseLars AhrenbergEnglishFrom Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder PipelineTianle Li, Wei-Lin Chiang, Evan Frick, et al.arXiv:2406.11939From Linguistics to Practice: a Case Study of Offensive Language Taxonomy in HebrewChaya Liebeskind, Marina Litvak, Natalia VanetikModern HebrewFrom YCOE to UD: Rule-based Root Identification in Old EnglishLuca Brigada Villa, Martina GiardaEnglishG-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question AnsweringXiaoxin He, Yijun Tian, Yifei Sun, et al.arXiv:2402.07630GDTB: Genre Diverse Data for English Shallow Discourse Parsing across Modalities, Text Types, and DomainsYang Janet Liu, Tatsuya Aoyama, Wesley Scivetti, et al.EnglishGemini 1.5: Unlocking multimodal understanding across millions of tokens of contextGemini Team, Petko Georgiev, Ving Ian Lei, et al.arXiv:2403.05530Generation and Evaluation of English Grammar Multiple-Choice Cloze ExercisesNicolò Donati, Matteo Periani, Paolo Di Natale, et al.EnglishGenerative Representational Instruction TuningNiklas Muennighoff, Hongjin Su, Liang Wang, et al.arXiv:2402.09906Generative Verifiers: Reward Modeling as Next-Token PredictionLunjun Zhang, Arian Hosseini, Hritik Bansal, et al.arXiv:2408.15240GPT-4o System CardOpenAI, Aaron Hurst, Adam Lerer, et al.arXiv:2410.21276GPT-4V(ision) is a Generalist Web Agent, if GroundedBoyuan Zheng, Boyu Gou, Jihyung Kil, et al.arXiv:2401.01614GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem SolversQintong Li, Leyang Cui, Xueliang Zhao, et al.Proceedings of the 62nd Annual Meeting of the…GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language ModelsIman Mirzadeh, Keivan Alizadeh, Hooman Shahrokhi, et al.arXiv:2410.05229Hallucination is Inevitable: An Innate Limitation of Large Language ModelsZiwei Xu, Sanjay Jain, Mohan KankanhalliarXiv:2401.118171 2 3