{"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/13","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":13,"pages_in_order":16,"rows_per_page":100,"rows":[1201,1300],"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/12","next":"/task/math/papers/14","papers":[{"url":null,"slug":"investigating-symbolic-capabilities-of-large","title":"Investigating Symbolic Capabilities of Large Language Models","date":"2024-05-21","arxiv_id":"2405.13209","repositories_listed":0,"syntology":null},{"url":null,"slug":"dop-diagnostic-oriented-prompting-for-large","title":"DOP: Diagnostic-Oriented Prompting for Large Language Models in Mathematical Correction","date":"2024-05-20","arxiv_id":"2405.12100","repositories_listed":0,"syntology":null},{"url":null,"slug":"metacognitive-capabilities-of-llms-an","title":"Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving","date":"2024-05-20","arxiv_id":"2405.12205","repositories_listed":0,"syntology":null},{"url":null,"slug":"continued-pretraining-for-domain-adaptation","title":"Continued Pretraining for Domain Adaptation of Wav2vec2.0 in Automatic Speech Recognition for Elementary Math Classroom Settings","date":"2024-05-15","arxiv_id":"2405.13018","repositories_listed":0,"syntology":null},{"url":null,"slug":"llms-are-meaning-typed-code-constructs","title":"Meaning-Typed Programming: Language Abstraction and Runtime for Model-Integrated Applications","date":"2024-05-14","arxiv_id":"2405.08965","repositories_listed":0,"syntology":null},{"url":null,"slug":"mathdivide-improved-mathematical-reasoning-by","title":"MathDivide: Improved mathematical reasoning by large language models","date":"2024-05-12","arxiv_id":"2405.13004","repositories_listed":0,"syntology":null},{"url":null,"slug":"aligning-tutor-discourse-supporting-rigorous","title":"Aligning Tutor Discourse Supporting Rigorous Thinking with Tutee Content Mastery for Predicting Math Achievement","date":"2024-05-10","arxiv_id":"2405.06218","repositories_listed":0,"syntology":null},{"url":null,"slug":"llms-can-find-mathematical-reasoning-mistakes","title":"LLMs can Find Mathematical Reasoning Mistakes by Pedagogical Chain-of-Thought","date":"2024-05-09","arxiv_id":"2405.06705","repositories_listed":0,"syntology":null},{"url":null,"slug":"mammoth2-scaling-instructions-from-the-web","title":"MAmmoTH2: Scaling Instructions from the Web","date":"2024-05-06","arxiv_id":"2405.03548","repositories_listed":0,"syntology":null},{"url":null,"slug":"assessing-and-verifying-task-utility-in-llm","title":"Assessing and Verifying Task Utility in LLM-Powered Applications","date":"2024-05-03","arxiv_id":"2405.02178","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-careful-examination-of-large-language-model","title":"A Careful Examination of Large Language Model Performance on Grade School Arithmetic","date":"2024-05-01","arxiv_id":"2405.00332","repositories_listed":0,"syntology":null},{"url":null,"slug":"math-multiple-choice-question-generation-via","title":"Math Multiple Choice Question Generation via Human-Large Language Model Collaboration","date":"2024-05-01","arxiv_id":"2405.00864","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-refine-instruction-tuning-for-aligning","title":"Self-Refine Instruction-Tuning for Aligning Reasoning in Language Models","date":"2024-05-01","arxiv_id":"2405.00402","repositories_listed":0,"syntology":null},{"url":null,"slug":"iterative-reasoning-preference-optimization","title":"Iterative Reasoning Preference Optimization","date":"2024-04-30","arxiv_id":"2404.19733","repositories_listed":0,"syntology":null},{"url":null,"slug":"describe-then-reason-improving-multimodal","title":"Describe-then-Reason: Improving Multimodal Mathematical Reasoning through Visual Comprehension Training","date":"2024-04-22","arxiv_id":"2404.14604","repositories_listed":0,"syntology":null},{"url":null,"slug":"paramanu-ganita-language-model-with","title":"PARAMANU-GANITA: Language Model with Mathematical Capabilities","date":"2024-04-22","arxiv_id":"2404.14395","repositories_listed":0,"syntology":null},{"url":"/paper/phi-3-technical-report-a-highly-capable","slug":"phi-3-technical-report-a-highly-capable","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","date":"2024-04-22","arxiv_id":"2404.14219","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-automated-distractor-generation-for","title":"Improving Automated Distractor Generation for Math Multiple-choice Questions with Overgenerate-and-rank","date":"2024-04-19","arxiv_id":"2405.05144","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-empirical-complexity-of-reasoning-and","title":"On the Empirical Complexity of Reasoning and Planning in LLMs","date":"2024-04-17","arxiv_id":"2404.11041","repositories_listed":0,"syntology":null},{"url":null,"slug":"mental-stress-detection-development-and","title":"Mental Stress Detection: Development and Evaluation of a Wearable In-Ear Plethysmography","date":"2024-04-12","arxiv_id":"2404.08212","repositories_listed":0,"syntology":null},{"url":null,"slug":"mathvc-an-llm-simulated-multi-character","title":"MathVC: An LLM-Simulated Multi-Character Virtual Classroom for Mathematics Education","date":"2024-04-10","arxiv_id":"2404.06711","repositories_listed":0,"syntology":null},{"url":null,"slug":"personality-aware-student-simulation-for","title":"Personality-aware Student Simulation for Conversational Intelligent Tutoring Systems","date":"2024-04-10","arxiv_id":"2404.06762","repositories_listed":0,"syntology":null},{"url":null,"slug":"fractal-fine-grained-scoring-from-aggregate","title":"FRACTAL: Fine-Grained Scoring from Aggregate Text Labels","date":"2024-04-07","arxiv_id":"2404.04817","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-augmentation-with-in-context-learning","title":"Data Augmentation with In-Context Learning and Comparative Evaluation in Math Word Problem Solving","date":"2024-04-05","arxiv_id":"2404.03938","repositories_listed":0,"syntology":null},{"url":null,"slug":"hyperclova-x-technical-report","title":"HyperCLOVA X Technical Report","date":"2024-04-02","arxiv_id":"2404.01954","repositories_listed":0,"syntology":null},{"url":null,"slug":"texttt-lm-texttt-2-a-simple-society-of","title":"$\\texttt{LM}^\\texttt{2}$: A Simple Society of Language Models Solves Complex Reasoning","date":"2024-04-02","arxiv_id":"2404.02255","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-mystery-of-influential-data-for","title":"Exploring the Mystery of Influential Data for Mathematical Reasoning","date":"2024-04-01","arxiv_id":"2404.01067","repositories_listed":0,"syntology":null},{"url":null,"slug":"isobench-benchmarking-multimodal-foundation","title":"IsoBench: Benchmarking Multimodal Foundation Models on Isomorphic Representations","date":"2024-04-01","arxiv_id":"2404.01266","repositories_listed":0,"syntology":null},{"url":null,"slug":"stable-code-technical-report","title":"Stable Code Technical Report","date":"2024-04-01","arxiv_id":"2404.01226","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-are-unconscious-of","title":"Large Language Models Are Struggle to Cope with Unreasonability in Math Problems","date":"2024-03-28","arxiv_id":"2403.19346","repositories_listed":0,"syntology":null},{"url":null,"slug":"ml2sc-deploying-machine-learning-models-as","title":"ML2SC: Deploying Machine Learning Models as Smart Contracts on the Blockchain","date":"2024-03-28","arxiv_id":"2404.16967","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-recalibration-of-language-models","title":"Few-Shot Recalibration of Language Models","date":"2024-03-27","arxiv_id":"2403.18286","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-invalsi-benchmark-measuring-language","title":"The Invalsi Benchmarks: measuring Linguistic and Mathematical understanding of Large Language Models in Italian","date":"2024-03-27","arxiv_id":"2403.18697","repositories_listed":0,"syntology":null},{"url":null,"slug":"automate-knowledge-concept-tagging-on-math","title":"Automate Knowledge Concept Tagging on Math Questions with LLMs","date":"2024-03-26","arxiv_id":"2403.17281","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-study-of-the-capabilities-of","title":"To Err is Machine: Vulnerability Detection Challenges LLM Reasoning","date":"2024-03-25","arxiv_id":"2403.17218","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-chain-of-thought-prompting-approach-with","title":"A Chain-of-Thought Prompting Approach with LLMs for Evaluating Students' Formative Assessment Responses in Science","date":"2024-03-21","arxiv_id":"2403.14565","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-large-to-tiny-distilling-and-refining","title":"From Large to Tiny: Distilling and Refining Mathematical Expertise for Math Word Problems with Weakly Supervision","date":"2024-03-21","arxiv_id":"2403.14390","repositories_listed":0,"syntology":null},{"url":"/paper/mathverse-does-your-multi-modal-llm-truly-see","slug":"mathverse-does-your-multi-modal-llm-truly-see","title":"MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?","date":"2024-03-21","arxiv_id":"2403.14624","repositories_listed":0,"syntology":null},{"url":null,"slug":"paramanu-ayn-an-efficient-novel-generative","title":"PARAMANU-AYN: Pretrain from scratch or Continual Pretraining of LLMs for Legal Domain Adaptation?","date":"2024-03-20","arxiv_id":"2403.13681","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-upper-bound-of-the-mutation-probability-in","title":"An upper bound of the mutation probability in the genetic algorithm for general 0-1 knapsack problem","date":"2024-03-17","arxiv_id":"2403.11307","repositories_listed":0,"syntology":null},{"url":null,"slug":"hydrodynamics-of-markets-hidden-links-between","title":"Hydrodynamics of Markets:Hidden Links Between Physics and Finance","date":"2024-03-14","arxiv_id":"2403.09761","repositories_listed":0,"syntology":null},{"url":null,"slug":"laying-the-foundation-first-investigating-the","title":"Laying the Foundation First? Investigating the Generalization from Atomic Skills to Complex Reasoning Tasks","date":"2024-03-14","arxiv_id":"2403.09479","repositories_listed":0,"syntology":null},{"url":null,"slug":"sabia-2-a-new-generation-of-portuguese-large","title":"Sabiá-2: A New Generation of Portuguese Large Language Models","date":"2024-03-14","arxiv_id":"2403.09887","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-consistency-boosts-calibration-for-math","title":"Self-Consistency Boosts Calibration for Math Reasoning","date":"2024-03-14","arxiv_id":"2403.09849","repositories_listed":0,"syntology":null},{"url":null,"slug":"mastering-text-code-and-math-simultaneously","title":"Mastering Text, Code and Math Simultaneously via Fusing Highly Specialized Language Models","date":"2024-03-13","arxiv_id":"2403.08281","repositories_listed":0,"syntology":null},{"url":null,"slug":"finemath-a-fine-grained-mathematical","title":"FineMath: A Fine-Grained Mathematical Evaluation Benchmark for Chinese Large Language Models","date":"2024-03-12","arxiv_id":"2403.07747","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-region-guidance-improving","title":"Contrastive Region Guidance: Improving Grounding in Vision-Language Models without Training","date":"2024-03-04","arxiv_id":"2403.02325","repositories_listed":0,"syntology":null},{"url":null,"slug":"experimenting-with-generative-ai-does-chatgpt","title":"Experimenting with Generative AI: Does ChatGPT Really Increase Everyone's Productivity?","date":"2024-03-04","arxiv_id":"2403.01770","repositories_listed":0,"syntology":null},{"url":"/paper/key-point-driven-data-synthesis-with-its","slug":"key-point-driven-data-synthesis-with-its","title":"Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning","date":"2024-03-04","arxiv_id":"2403.02333","repositories_listed":0,"syntology":null},{"url":"/paper/the-claude-3-model-family-opus-sonnet-haiku","slug":"the-claude-3-model-family-opus-sonnet-haiku","title":"The Claude 3 Model Family: Opus, Sonnet, Haiku","date":"2024-03-04","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"clicktree-a-tree-based-method-for-predicting","title":"ClickTree: A Tree-based Method for Predicting Math Students' Performance Based on Clickstream Data","date":"2024-03-01","arxiv_id":"2403.14664","repositories_listed":0,"syntology":null},{"url":null,"slug":"prsa-prompt-reverse-stealing-attacks-against","title":"PRSA: Prompt Stealing Attacks against Real-World Prompt Services","date":"2024-02-29","arxiv_id":"2402.19200","repositories_listed":0,"syntology":null},{"url":null,"slug":"mathgenie-generating-synthetic-data-with","title":"MathGenie: Generating Synthetic Data with Question Back-translation for Enhancing Mathematical Reasoning of LLMs","date":"2024-02-26","arxiv_id":"2402.16352","repositories_listed":0,"syntology":null},{"url":null,"slug":"brain-inspired-two-stage-approach-enhancing","title":"Brain-Inspired Two-Stage Approach: Enhancing Mathematical Reasoning by Imitating Human Thought Processes","date":"2024-02-23","arxiv_id":"2403.00800","repositories_listed":0,"syntology":null},{"url":null,"slug":"lora-flow-dynamic-lora-fusion-for-large","title":"LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks","date":"2024-02-18","arxiv_id":"2402.11455","repositories_listed":0,"syntology":null},{"url":"/paper/orca-math-unlocking-the-potential-of-slms-in","slug":"orca-math-unlocking-the-potential-of-slms-in","title":"Orca-Math: Unlocking the potential of SLMs in Grade School Math","date":"2024-02-16","arxiv_id":"2402.14830","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-models-with-conformal-factuality","title":"Language Models with Conformal Factuality Guarantees","date":"2024-02-15","arxiv_id":"2402.10978","repositories_listed":0,"syntology":null},{"url":null,"slug":"mathematical-opportunities-in-digital-twins","title":"Mathematical Opportunities in Digital Twins (MATH-DT)","date":"2024-02-15","arxiv_id":"2402.10326","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-better-human-agent-alignment","title":"Towards better Human-Agent Alignment: Assessing Task Utility in LLM-Powered Applications","date":"2024-02-14","arxiv_id":"2402.09015","repositories_listed":0,"syntology":null},{"url":null,"slug":"glore-when-where-and-how-to-improve-llm","title":"GLoRe: When, Where, and How to Improve LLM Reasoning via Global and Local Refinements","date":"2024-02-13","arxiv_id":"2402.10963","repositories_listed":0,"syntology":null},{"url":null,"slug":"evogpt-f-an-evolutionary-gpt-framework-for","title":"EvoGPT-f: An Evolutionary GPT Framework for Benchmarking Formal Math Languages","date":"2024-02-12","arxiv_id":"2402.16878","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-the-progression-of-educational","title":"Understanding the Progression of Educational Topics via Semantic Matching","date":"2024-02-10","arxiv_id":"2403.05553","repositories_listed":0,"syntology":null},{"url":null,"slug":"v-star-training-verifiers-for-self-taught","title":"V-STaR: Training Verifiers for Self-Taught Reasoners","date":"2024-02-09","arxiv_id":"2402.06457","repositories_listed":0,"syntology":null},{"url":null,"slug":"revorder-a-novel-method-for-enhanced","title":"RevOrder: A Novel Method for Enhanced Arithmetic in Language Models","date":"2024-02-06","arxiv_id":"2402.03822","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-step-problem-solving-through-a-verifier","title":"Multi-step Problem Solving Through a Verifier: An Empirical Analysis on Model-induced Process Supervision","date":"2024-02-05","arxiv_id":"2402.02658","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-assessment-of-tutoring-practices","title":"Improving Assessment of Tutoring Practices using Retrieval-Augmented Generation","date":"2024-02-04","arxiv_id":"2402.14594","repositories_listed":0,"syntology":null},{"url":null,"slug":"salsa-fresca-angular-embeddings-and-pre","title":"Salsa Fresca: Angular Embeddings and Pre-Training for ML Attacks on Learning With Errors","date":"2024-02-02","arxiv_id":"2402.01082","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-for-mathematical","title":"Large Language Models for Mathematical Reasoning: Progresses and Challenges","date":"2024-01-31","arxiv_id":"2402.00157","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-tool-use-with-chain-of-abstraction","title":"Efficient Tool Use with Chain-of-Abstraction Reasoning","date":"2024-01-30","arxiv_id":"2401.17464","repositories_listed":0,"syntology":null},{"url":"/paper/gaps-geometry-aware-problem-solver","slug":"gaps-geometry-aware-problem-solver","title":"GAPS: Geometry-Aware Problem Solver","date":"2024-01-29","arxiv_id":"2401.16287","repositories_listed":0,"syntology":null},{"url":null,"slug":"yoda-teacher-student-progressive-learning-for","title":"YODA: Teacher-Student Progressive Learning for Language Models","date":"2024-01-28","arxiv_id":"2401.15670","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-educational-equity-a-machine","title":"Exploring Educational Equity: A Machine Learning Approach to Unravel Achievement Disparities in Georgia","date":"2024-01-25","arxiv_id":"2402.01710","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-java-geometry-expert-as-guide-in-the","title":"Using Java Geometry Expert as Guide in the Preparations for Math Contests","date":"2024-01-22","arxiv_id":"2401.13704","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-imagine-effective-unimodal-reasoning","title":"Self-Imagine: Effective Unimodal Reasoning with Multimodal Models using Self-Imagination","date":"2024-01-16","arxiv_id":"2401.08025","repositories_listed":0,"syntology":null},{"url":null,"slug":"champ-a-competition-level-dataset-for-fine","title":"CHAMP: A Competition-level Dataset for Fine-Grained Analyses of LLMs' Mathematical Reasoning Capabilities","date":"2024-01-13","arxiv_id":"2401.06961","repositories_listed":0,"syntology":null},{"url":null,"slug":"cramer-rao-bound-and-absolute-sensitivity-in","title":"Cramer-Rao bound and absolute sensitivity in chemical reaction networks","date":"2024-01-13","arxiv_id":"2401.06987","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-large-language-models-to-assess-tutors","title":"Using Large Language Models to Assess Tutors' Performance in Reacting to Students Making Math Errors","date":"2024-01-06","arxiv_id":"2401.03238","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph2tac-learning-hierarchical","title":"Graph2Tac: Online Representation Learning of Formal Math Concepts","date":"2024-01-05","arxiv_id":"2401.02949","repositories_listed":0,"syntology":null},{"url":null,"slug":"mastery-guided-non-parametric-clustering-to","title":"Mastery Guided Non-parametric Clustering to Scale-up Strategy Prediction","date":"2024-01-04","arxiv_id":"2401.10210","repositories_listed":0,"syntology":null},{"url":null,"slug":"assessing-the-impact-of-prompting-persona-and","title":"Assessing the Impact of Prompting Methods on ChatGPT's Mathematical Capabilities","date":"2023-12-22","arxiv_id":"2312.15006","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-good-to-great-improving-math-reasoning","title":"From Good to Great: Improving Math Reasoning with Tool-Augmented Interleaf Prompting","date":"2023-12-18","arxiv_id":"2401.05384","repositories_listed":0,"syntology":null},{"url":"/paper/boosting-llm-reasoning-push-the-limits-of-few","slug":"boosting-llm-reasoning-push-the-limits-of-few","title":"Fewer is More: Boosting LLM Reasoning with Reinforced Context Pruning","date":"2023-12-14","arxiv_id":"2312.08901","repositories_listed":0,"syntology":null},{"url":"/paper/tinygsm-achieving-80-on-gsm8k-with-small","slug":"tinygsm-achieving-80-on-gsm8k-with-small","title":"TinyGSM: achieving >80% on GSM8k with small language models","date":"2023-12-14","arxiv_id":"2312.09241","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-human-data-scaling-self-training-for","title":"Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models","date":"2023-12-11","arxiv_id":"2312.06585","repositories_listed":0,"syntology":null},{"url":null,"slug":"latent-skill-discovery-for-chain-of-thought","title":"LaRS: Latent Reasoning Skills for Chain-of-Thought Reasoning","date":"2023-12-07","arxiv_id":"2312.04684","repositories_listed":0,"syntology":null},{"url":null,"slug":"first-step-advantage-importance-of-starting","title":"First-Step Advantage: Importance of Starting Right in Multi-Step Math Reasoning","date":"2023-11-14","arxiv_id":"2311.07945","repositories_listed":0,"syntology":null},{"url":null,"slug":"saie-framework-support-alone-isn-t-enough","title":"SAIE Framework: Support Alone Isn't Enough -- Advancing LLM Training with Adversarial Remarks","date":"2023-11-14","arxiv_id":"2311.08107","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-understanding-of-math","title":"Large Language Models' Understanding of Math: Source Criticism and Extrapolation","date":"2023-11-12","arxiv_id":"2311.07618","repositories_listed":0,"syntology":null},{"url":null,"slug":"let-s-reinforce-step-by-step","title":"Let's Reinforce Step by Step","date":"2023-11-10","arxiv_id":"2311.05821","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-llm-intelligence-with-arm-rag","title":"Enhancing LLM Intelligence with ARM-RAG: Auxiliary Rationale Memory for Retrieval Augmented Generation","date":"2023-11-07","arxiv_id":"2311.04177","repositories_listed":0,"syntology":null},{"url":null,"slug":"math-pvs-a-large-language-model-framework-to","title":"math-PVS: A Large Language Model Framework to Map Scientific Publications to PVS Theories","date":"2023-10-25","arxiv_id":"2310.17064","repositories_listed":0,"syntology":null},{"url":null,"slug":"sego-sequential-subgoal-optimization-for","title":"SEGO: Sequential Subgoal Optimization for Mathematical Problem-Solving","date":"2023-10-19","arxiv_id":"2310.12960","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-large-language-model-fine-tuning","title":"Improving Large Language Model Fine-tuning for Solving Math Problems","date":"2023-10-16","arxiv_id":"2310.10047","repositories_listed":0,"syntology":null},{"url":null,"slug":"let-s-reward-step-by-step-step-level-reward","title":"Let's reward step by step: Step-Level reward model as the Navigators for Reasoning","date":"2023-10-16","arxiv_id":"2310.10080","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-search-and-mix-paradigm-in-approximate","title":"The Search-and-Mix Paradigm in Approximate Nash Equilibrium Algorithms","date":"2023-10-12","arxiv_id":"2310.08066","repositories_listed":0,"syntology":null},{"url":null,"slug":"llms-as-potential-brainstorming-partners-for","title":"LLMs as Potential Brainstorming Partners for Math and Science Problems","date":"2023-10-10","arxiv_id":"2310.10677","repositories_listed":0,"syntology":null},{"url":null,"slug":"guiding-language-model-reasoning-with","title":"Guiding Language Model Reasoning with Planning Tokens","date":"2023-10-09","arxiv_id":"2310.05707","repositories_listed":0,"syntology":null},{"url":null,"slug":"critique-ability-of-large-language-models","title":"Critique Ability of Large Language Models","date":"2023-10-07","arxiv_id":"2310.04815","repositories_listed":0,"syntology":null},{"url":null,"slug":"resprompt-residual-connection-prompting","title":"Resprompt: Residual Connection Prompting Advances Multi-Step Reasoning in Large Language Models","date":"2023-10-07","arxiv_id":"2310.04743","repositories_listed":0,"syntology":null},{"url":null,"slug":"analysis-of-the-reasoning-with-redundant","title":"Analysis of the Reasoning with Redundant Information Provided Ability of Large Language Models","date":"2023-10-06","arxiv_id":"2310.04039","repositories_listed":0,"syntology":null}],"record_sha256":"a525f802980bc7afcc226d0179aae130f26bcaa058c220c265e908791b97661b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}