{"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/math/papers/11","list_of":"/task/math","task":"Math","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":11,"pages_in_order":16,"rows_per_page":100,"rows":[1001,1100],"of":1596,"counts":{"archive_papers_tagged":1596,"with_a_code_link":765,"where_syntology_ran_a_sample":349,"not_listed_spam_title":0,"listed":1596,"listed_where_code_ran":349,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":286,"every_run_a_failure_of_syntologys_instrument":63,"listed_with_a_run_with_no_instrument_failure":286,"listed_every_run_a_failure_of_syntologys_instrument":63,"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/math","prev":"/task/math/papers/10","next":"/task/math/papers/12","papers":[{"url":null,"slug":"clear-preferences-leave-traces-reference","title":"Clear Preferences Leave Traces: Reference Model-Guided Sampling for Preference Learning","date":"2025-01-25","arxiv_id":"2501.15109","repositories_listed":0,"syntology":null},{"url":null,"slug":"drawedumath-evaluating-vision-language-models","title":"DrawEduMath: Evaluating Vision Language Models with Expert-Annotated Students' Hand-Drawn Math Images","date":"2025-01-24","arxiv_id":"2501.14877","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-math-reasoning-in-language-models","title":"Advancing Mathematical Reasoning in Language Models: The Impact of Problem-Solving Data, Data Synthesis Methods, and Training Stages","date":"2025-01-23","arxiv_id":"2501.14002","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-optimal-transport-approach-to-arbitrage","title":"An Optimal Transport approach to arbitrage correction: Application to volatility Stress-Tests","date":"2025-01-21","arxiv_id":"2501.12195","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-your-llm-trapped-in-a-mental-set","title":"Is your LLM trapped in a Mental Set? Investigative study on how mental sets affect the reasoning capabilities of LLMs","date":"2025-01-21","arxiv_id":"2501.11833","repositories_listed":0,"syntology":null},{"url":null,"slug":"redstar-does-scaling-long-cot-data-unlock","title":"RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?","date":"2025-01-20","arxiv_id":"2501.11284","repositories_listed":0,"syntology":null},{"url":null,"slug":"chain-of-reasoning-towards-unified","title":"Chain-of-Reasoning: Towards Unified Mathematical Reasoning in Large Language Models via a Multi-Paradigm Perspective","date":"2025-01-19","arxiv_id":"2501.11110","repositories_listed":0,"syntology":null},{"url":null,"slug":"step-kto-optimizing-mathematical-reasoning","title":"Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback","date":"2025-01-18","arxiv_id":"2501.10799","repositories_listed":0,"syntology":null},{"url":null,"slug":"cascaded-self-evaluation-augmented-training","title":"Cascaded Self-Evaluation Augmented Training for Efficient Multimodal Large Language Models","date":"2025-01-10","arxiv_id":"2501.05662","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-general-retrieval-augmented-generation","title":"A General Retrieval-Augmented Generation Framework for Multimodal Case-Based Reasoning Applications","date":"2025-01-09","arxiv_id":"2501.05030","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-bangla-ai-for-solving-math","title":"End-to-End Bangla AI for Solving Math Olympiad Problem Benchmark: Leveraging Large Language Model Using Integrated Approach","date":"2025-01-08","arxiv_id":"2501.04425","repositories_listed":0,"syntology":null},{"url":null,"slug":"infifusion-a-unified-framework-for-enhanced","title":"InfiFusion: A Unified Framework for Enhanced Cross-Model Reasoning via LLM Fusion","date":"2025-01-06","arxiv_id":"2501.02795","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantization-meets-reasoning-exploring-llm","title":"Quantization Meets Reasoning: Exploring LLM Low-Bit Quantization Degradation for Mathematical Reasoning","date":"2025-01-06","arxiv_id":"2501.03035","repositories_listed":0,"syntology":null},{"url":null,"slug":"empowering-bengali-education-with-ai-solving","title":"Empowering Bengali Education with AI: Solving Bengali Math Word Problems through Transformer Models","date":"2025-01-05","arxiv_id":"2501.02599","repositories_listed":0,"syntology":null},{"url":null,"slug":"understand-solve-and-translate-bridging-the","title":"Understand, Solve and Translate: Bridging the Multilingual Mathematical Reasoning Gap","date":"2025-01-05","arxiv_id":"2501.02448","repositories_listed":0,"syntology":null},{"url":null,"slug":"instruction-following-pruning-for-large","title":"Instruction-Following Pruning for Large Language Models","date":"2025-01-03","arxiv_id":"2501.02086","repositories_listed":0,"syntology":null},{"url":null,"slug":"recursive-decomposition-of-logical-thoughts","title":"Recursive Decomposition of Logical Thoughts: Framework for Superior Reasoning and Knowledge Propagation in Large Language Models","date":"2025-01-03","arxiv_id":"2501.02026","repositories_listed":0,"syntology":null},{"url":null,"slug":"experimental-demonstration-of-an-optical","title":"Experimental Demonstration of an Optical Neural PDE Solver via On-Chip PINN Training","date":"2025-01-01","arxiv_id":"2501.00742","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethink-delay-doppler-channels-and-time","title":"Rethink Delay Doppler Channels and Time-Frequency Coding","date":"2024-12-31","arxiv_id":"2501.00641","repositories_listed":0,"syntology":null},{"url":null,"slug":"measuring-large-language-models-capacity-to","title":"Measuring Large Language Models Capacity to Annotate Journalistic Sourcing","date":"2024-12-30","arxiv_id":"2501.00164","repositories_listed":0,"syntology":null},{"url":null,"slug":"slow-perception-let-s-perceive-geometric","title":"Slow Perception: Let's Perceive Geometric Figures Step-by-step","date":"2024-12-30","arxiv_id":"2412.20631","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-skill-adaptation-for-large-language","title":"Dynamic Skill Adaptation for Large Language Models","date":"2024-12-26","arxiv_id":"2412.19361","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-the-design-features-of-an","title":"Evaluating the Design Features of an Intelligent Tutoring System for Advanced Mathematics Learning","date":"2024-12-23","arxiv_id":"2412.17265","repositories_listed":0,"syntology":null},{"url":null,"slug":"structtest-benchmarking-llms-reasoning","title":"StructTest: Benchmarking LLMs' Reasoning through Compositional Structured Outputs","date":"2024-12-23","arxiv_id":"2412.18011","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-intrinsic-self-correction-enhancement","title":"Towards Intrinsic Self-Correction Enhancement in Monte Carlo Tree Search Boosted Reasoning via Iterative Preference Learning","date":"2024-12-23","arxiv_id":"2412.17397","repositories_listed":0,"syntology":null},{"url":null,"slug":"ask-before-detection-identifying-and","title":"Ask-Before-Detection: Identifying and Mitigating Conformity Bias in LLM-Powered Error Detector for Math Word Problem Solutions","date":"2024-12-22","arxiv_id":"2412.16838","repositories_listed":0,"syntology":null},{"url":null,"slug":"system-2-mathematical-reasoning-via-enriched","title":"System-2 Mathematical Reasoning via Enriched Instruction Tuning","date":"2024-12-22","arxiv_id":"2412.16964","repositories_listed":0,"syntology":null},{"url":null,"slug":"correct-implied-volatility-shapes-and","title":"Correct implied volatility shapes and reliable pricing in the rough Heston model","date":"2024-12-20","arxiv_id":"2412.16067","repositories_listed":0,"syntology":null},{"url":null,"slug":"ensembling-large-language-models-with-process","title":"Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoning","date":"2024-12-20","arxiv_id":"2412.15797","repositories_listed":0,"syntology":null},{"url":null,"slug":"formal-mathematical-reasoning-a-new-frontier","title":"Formal Mathematical Reasoning: A New Frontier in AI","date":"2024-12-20","arxiv_id":"2412.16075","repositories_listed":0,"syntology":null},{"url":null,"slug":"acemath-advancing-frontier-math-reasoning","title":"AceMath: Advancing Frontier Math Reasoning with Post-Training and Reward Modeling","date":"2024-12-19","arxiv_id":"2412.15084","repositories_listed":0,"syntology":null},{"url":null,"slug":"conceptual-in-context-learning-and-chain-of","title":"Conceptual In-Context Learning and Chain of Concepts: Solving Complex Conceptual Problems Using Large Language Models","date":"2024-12-19","arxiv_id":"2412.15309","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-for-mathematical-copilots-better-ways-of","title":"Data for Mathematical Copilots: Better Ways of Presenting Proofs for Machine Learning","date":"2024-12-19","arxiv_id":"2412.15184","repositories_listed":0,"syntology":null},{"url":null,"slug":"inference-aware-fine-tuning-for-best-of-n","title":"Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models","date":"2024-12-18","arxiv_id":"2412.15287","repositories_listed":0,"syntology":null},{"url":null,"slug":"strictly-monotone-mean-variance-preferences","title":"Strictly monotone mean-variance preferences with applications to portfolio selection","date":"2024-12-18","arxiv_id":"2412.13523","repositories_listed":0,"syntology":null},{"url":null,"slug":"lingualift-an-effective-two-stage-instruction","title":"LinguaLIFT: An Effective Two-stage Instruction Tuning Framework for Low-Resource Language Tasks","date":"2024-12-17","arxiv_id":"2412.12499","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-mathematical-reasoning-in-the-era","title":"A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges","date":"2024-12-16","arxiv_id":"2412.11936","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-graph-based-synthetic-data-pipeline-for","title":"A Graph-Based Synthetic Data Pipeline for Scaling High-Quality Reasoning Instructions","date":"2024-12-12","arxiv_id":"2412.08864","repositories_listed":0,"syntology":null},{"url":null,"slug":"dipper-diversity-in-prompts-for-producing","title":"Dipper: Diversity in Prompts for Producing Large Language Model Ensembles in Reasoning tasks","date":"2024-12-12","arxiv_id":"2412.15238","repositories_listed":0,"syntology":null},{"url":null,"slug":"geo-llava-a-large-multi-modal-model-for","title":"Geo-LLaVA: A Large Multi-Modal Model for Solving Geometry Math Problems with Meta In-Context Learning","date":"2024-12-12","arxiv_id":"2412.10455","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-solve-domain-specific-calculation","title":"Learning to Solve Domain-Specific Calculation Problems with Knowledge-Intensive Programs Generator","date":"2024-12-12","arxiv_id":"2412.09280","repositories_listed":0,"syntology":null},{"url":null,"slug":"greek2mathtex-a-greek-speech-to-text","title":"Greek2MathTex: A Greek Speech-to-Text Framework for LaTeX Equations Generation","date":"2024-12-11","arxiv_id":"2412.12167","repositories_listed":0,"syntology":null},{"url":null,"slug":"mnist-fraction-enhancing-math-education-with","title":"MNIST-Fraction: Enhancing Math Education with AI-Driven Fraction Detection and Analysis","date":"2024-12-11","arxiv_id":"2412.08633","repositories_listed":0,"syntology":null},{"url":null,"slug":"mining-math-conjectures-from-llms-a-pruning","title":"Mining Math Conjectures from LLMs: A Pruning Approach","date":"2024-12-09","arxiv_id":"2412.16177","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-dimensionality-reduction-meets-graph","title":"When Dimensionality Reduction Meets Graph (Drawing) Theory: Introducing a Common Framework, Challenges and Opportunities","date":"2024-12-09","arxiv_id":"2412.06555","repositories_listed":0,"syntology":null},{"url":null,"slug":"chimera-improving-generalist-model-with","title":"Chimera: Improving Generalist Model with Domain-Specific Experts","date":"2024-12-08","arxiv_id":"2412.05983","repositories_listed":0,"syntology":null},{"url":null,"slug":"hard-math-easy-uvm-pragmatic-solutions-for","title":"Hard Math -- Easy UVM: Pragmatic solutions for verifying hardware algorithms using UVM","date":"2024-12-06","arxiv_id":"2412.04919","repositories_listed":0,"syntology":null},{"url":null,"slug":"neuro-symbolic-data-generation-for-math","title":"Neuro-Symbolic Data Generation for Math Reasoning","date":"2024-12-06","arxiv_id":"2412.04857","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-latex-code-generation-from","title":"Automated LaTeX Code Generation from Handwritten Math Expressions Using Vision Transformer","date":"2024-12-05","arxiv_id":"2412.03853","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-mathematical-reasoning-in-llms-with","title":"Enhancing Mathematical Reasoning in LLMs with Background Operators","date":"2024-12-05","arxiv_id":"2412.04110","repositories_listed":0,"syntology":null},{"url":null,"slug":"redstone-curating-general-code-math-and-qa","title":"RedStone: Curating General, Code, Math, and QA Data for Large Language Models","date":"2024-12-04","arxiv_id":"2412.03398","repositories_listed":0,"syntology":null},{"url":null,"slug":"malt-improving-reasoning-with-multi-agent-llm","title":"MALT: Improving Reasoning with Multi-Agent LLM Training","date":"2024-12-02","arxiv_id":"2412.01928","repositories_listed":0,"syntology":null},{"url":null,"slug":"yi-lightning-technical-report","title":"Yi-Lightning Technical Report","date":"2024-12-02","arxiv_id":"2412.01253","repositories_listed":0,"syntology":null},{"url":null,"slug":"reverse-thinking-makes-llms-stronger","title":"Reverse Thinking Makes LLMs Stronger Reasoners","date":"2024-11-29","arxiv_id":"2411.19865","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-lean-dataset-for-international-math","title":"A Lean Dataset for International Math Olympiad: Small Steps towards Writing Math Proofs for Hard Problems","date":"2024-11-28","arxiv_id":"2411.18872","repositories_listed":0,"syntology":null},{"url":null,"slug":"mars-po-multi-agent-reasoning-system","title":"Mars-PO: Multi-Agent Reasoning System Preference Optimization","date":"2024-11-28","arxiv_id":"2411.19039","repositories_listed":0,"syntology":null},{"url":null,"slug":"embracing-ai-in-education-understanding-the","title":"Embracing AI in Education: Understanding the Surge in Large Language Model Use by Secondary Students","date":"2024-11-27","arxiv_id":"2411.18708","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-by-analogy-enhancing-few-shot","title":"Learning by Analogy: Enhancing Few-Shot Prompting for Math Word Problem Solving with Computational Graph-Based Retrieval","date":"2024-11-25","arxiv_id":"2411.16454","repositories_listed":0,"syntology":null},{"url":null,"slug":"unraveling-arithmetic-in-large-language","title":"Unraveling Arithmetic in Large Language Models: The Role of Algebraic Structures","date":"2024-11-25","arxiv_id":"2411.16260","repositories_listed":0,"syntology":null},{"url":null,"slug":"velocitune-a-velocity-based-dynamic-domain","title":"Velocitune: A Velocity-based Dynamic Domain Reweighting Method for Continual Pre-training","date":"2024-11-21","arxiv_id":"2411.14318","repositories_listed":0,"syntology":null},{"url":null,"slug":"openai-o1-ab-testing-does-the-o1-model-really","title":"OpenAI-o1 AB Testing: Does the o1 model really do good reasoning in math problem solving?","date":"2024-11-09","arxiv_id":"2411.06198","repositories_listed":0,"syntology":null},{"url":null,"slug":"vista-visual-integrated-system-for-tailored","title":"VISTA: Visual Integrated System for Tailored Automation in Math Problem Generation Using LLM","date":"2024-11-08","arxiv_id":"2411.05423","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-gpt-4-at-grading-handwritten","title":"Evaluating GPT-4 at Grading Handwritten Solutions in Math Exams","date":"2024-11-07","arxiv_id":"2411.05231","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-consistency-preference-optimization","title":"Self-Consistency Preference Optimization","date":"2024-11-06","arxiv_id":"2411.04109","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-generation-of-question-hints-for","title":"Automatic Generation of Question Hints for Mathematics Problems using Large Language Models in Educational Technology","date":"2024-11-05","arxiv_id":"2411.03495","repositories_listed":0,"syntology":null},{"url":null,"slug":"dictionary-insertion-prompting-for","title":"Dictionary Insertion Prompting for Multilingual Reasoning on Multilingual Large Language Models","date":"2024-11-02","arxiv_id":"2411.01141","repositories_listed":0,"syntology":null},{"url":"/paper/stem-pom-evaluating-language-models-math","slug":"stem-pom-evaluating-language-models-math","title":"STEM-POM: Evaluating Language Models Math-Symbol Reasoning in Document Parsing","date":"2024-11-01","arxiv_id":"2411.00387","repositories_listed":0,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/stem-pom-evaluating-language-models-math#ran","syntology_url":"https://syntology.ai/paper/2411.00387","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00387"}},"official":null}},{"url":null,"slug":"automated-feedback-in-math-education-a","title":"Automated Feedback in Math Education: A Comparative Analysis of LLMs for Open-Ended Responses","date":"2024-10-29","arxiv_id":"2411.08910","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamath-a-dynamic-visual-benchmark-for","title":"DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models","date":"2024-10-29","arxiv_id":"2411.00836","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-math-problem-solving-in-large","title":"Improving Math Problem Solving in Large Language Models Through Categorization and Strategy Tailoring","date":"2024-10-29","arxiv_id":"2411.00042","repositories_listed":0,"syntology":null},{"url":"/paper/eora-training-free-compensation-for","slug":"eora-training-free-compensation-for","title":"EoRA: Training-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation","date":"2024-10-28","arxiv_id":"2410.21271","repositories_listed":0,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/eora-training-free-compensation-for#ran","syntology_url":"https://syntology.ai/paper/2410.21271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21271"}},"official":null}},{"url":null,"slug":"can-stories-help-llms-reason-curating","title":"Can Stories Help LLMs Reason? Curating Information Space Through Narrative","date":"2024-10-25","arxiv_id":"2410.19221","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-blind-solvers-to-logical-thinkers","title":"From Blind Solvers to Logical Thinkers: Benchmarking LLMs' Logical Integrity on Faulty Mathematical Problems","date":"2024-10-24","arxiv_id":"2410.18921","repositories_listed":0,"syntology":null},{"url":null,"slug":"mixture-of-parrots-experts-improve","title":"Mixture of Parrots: Experts improve memorization more than reasoning","date":"2024-10-24","arxiv_id":"2410.19034","repositories_listed":0,"syntology":null},{"url":null,"slug":"reasonagain-using-extractable-symbolic","title":"ReasonAgain: Using Extractable Symbolic Programs to Evaluate Mathematical Reasoning","date":"2024-10-24","arxiv_id":"2410.19056","repositories_listed":0,"syntology":null},{"url":null,"slug":"milora-efficient-mixture-of-low-rank","title":"MiLoRA: Efficient Mixture of Low-Rank Adaptation for Large Language Models Fine-tuning","date":"2024-10-23","arxiv_id":"2410.18035","repositories_listed":0,"syntology":null},{"url":null,"slug":"forewarned-is-forearmed-leveraging-llms-for","title":"Forewarned is Forearmed: Leveraging LLMs for Data Synthesis through Failure-Inducing Exploration","date":"2024-10-22","arxiv_id":"2410.16736","repositories_listed":0,"syntology":null},{"url":null,"slug":"jmmmu-a-japanese-massive-multi-discipline","title":"JMMMU: A Japanese Massive Multi-discipline Multimodal Understanding Benchmark for Culture-aware Evaluation","date":"2024-10-22","arxiv_id":"2410.17250","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-chain-of-thought-reasoning","title":"Optimizing Chain-of-Thought Reasoning: Tackling Arranging Bottleneck via Plan Augmentation","date":"2024-10-22","arxiv_id":"2410.16812","repositories_listed":0,"syntology":null},{"url":null,"slug":"polyak-s-heavy-ball-method-achieves","title":"Polyak's Heavy Ball Method Achieves Accelerated Local Rate of Convergence under Polyak-Lojasiewicz Inequality","date":"2024-10-22","arxiv_id":"2410.16849","repositories_listed":0,"syntology":null},{"url":null,"slug":"no-more-hard-prompts-softsrv-prompting-for","title":"No more hard prompts: SoftSRV prompting for synthetic data generation","date":"2024-10-21","arxiv_id":"2410.16534","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompthive-bringing-subject-matter-experts","title":"PromptHive: Bringing Subject Matter Experts Back to the Forefront with Collaborative Prompt Engineering for Educational Content Creation","date":"2024-10-21","arxiv_id":"2410.16547","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-large-language-models-truly-grasp","title":"Do Large Language Models Truly Grasp Mathematics? An Empirical Exploration From Cognitive Psychology","date":"2024-10-19","arxiv_id":"2410.14979","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-designing-effective-rl-reward-at-training","title":"On Designing Effective RL Reward at Training Time for LLM Reasoning","date":"2024-10-19","arxiv_id":"2410.15115","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-the-training-inference-gap-in-llms","title":"Bridging the Training-Inference Gap in LLMs by Leveraging Self-Generated Tokens","date":"2024-10-18","arxiv_id":"2410.14655","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-the-genius-paradox-a-linguistic-and-math","title":"LLM The Genius Paradox: A Linguistic and Math Expert's Struggle with Simple Word-based Counting Problems","date":"2024-10-18","arxiv_id":"2410.14166","repositories_listed":0,"syntology":null},{"url":null,"slug":"step-guided-reasoning-improving-mathematical","title":"Step Guided Reasoning: Improving Mathematical Reasoning using Guidance Generation and Step Reasoning","date":"2024-10-18","arxiv_id":"2410.19817","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-not-to-answer-evaluating-prompts-on-gpt","title":"When Not to Answer: Evaluating Prompts on GPT Models for Effective Abstention in Unanswerable Math Word Problems","date":"2024-10-16","arxiv_id":"2410.13029","repositories_listed":0,"syntology":null},{"url":null,"slug":"mind-math-informed-synthetic-dialogues-for","title":"MIND: Math Informed syNthetic Dialogues for Pretraining LLMs","date":"2024-10-15","arxiv_id":"2410.12881","repositories_listed":0,"syntology":null},{"url":null,"slug":"speculative-knowledge-distillation-bridging","title":"Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling","date":"2024-10-15","arxiv_id":"2410.11325","repositories_listed":0,"syntology":null},{"url":null,"slug":"embedding-self-correction-as-an-inherent","title":"Embedding Self-Correction as an Inherent Ability in Large Language Models for Enhanced Mathematical Reasoning","date":"2024-10-14","arxiv_id":"2410.10735","repositories_listed":0,"syntology":null},{"url":null,"slug":"innovative-thinking-infinite-humor-humor","title":"Innovative Thinking, Infinite Humor: Humor Research of Large Language Models through Structured Thought Leaps","date":"2024-10-14","arxiv_id":"2410.10370","repositories_listed":0,"syntology":null},{"url":null,"slug":"dualformer-controllable-fast-and-slow","title":"Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces","date":"2024-10-13","arxiv_id":"2410.09918","repositories_listed":0,"syntology":null},{"url":null,"slug":"expanding-search-space-with-diverse-prompting","title":"Expanding Search Space with Diverse Prompting Agents: An Efficient Sampling Approach for LLM Mathematical Reasoning","date":"2024-10-13","arxiv_id":"2410.09780","repositories_listed":0,"syntology":null},{"url":null,"slug":"testing-gpt-4-o1-preview-on-math-and-science","title":"Testing GPT-4-o1-preview on math and science problems: A follow-up study","date":"2024-10-11","arxiv_id":"2410.22340","repositories_listed":0,"syntology":null},{"url":null,"slug":"cognitive-noise-and-altruistic-preferences","title":"Cognitive Noise and Altruistic Preferences","date":"2024-10-10","arxiv_id":"2410.07647","repositories_listed":0,"syntology":null},{"url":null,"slug":"hallucinating-ai-hijacking-attack-large","title":"Hallucinating AI Hijacking Attack: Large Language Models and Malicious Code Recommenders","date":"2024-10-09","arxiv_id":"2410.06462","repositories_listed":0,"syntology":null},{"url":null,"slug":"herald-a-natural-language-annotated-lean-4","title":"Herald: A Natural Language Annotated Lean 4 Dataset","date":"2024-10-09","arxiv_id":"2410.10878","repositories_listed":0,"syntology":null},{"url":null,"slug":"subtle-errors-matter-preference-learning-via","title":"Subtle Errors Matter: Preference Learning via Error-injected Self-editing","date":"2024-10-09","arxiv_id":"2410.06638","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-captioning-task-specific-prompting-for","title":"Beyond Captioning: Task-Specific Prompting for Improved VLM Performance in Mathematical Reasoning","date":"2024-10-08","arxiv_id":"2410.05928","repositories_listed":0,"syntology":null}],"record_sha256":"8e064b572f45455f5de59351926e67de172f951a235a509e1d18081eca7d0c25","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}