{"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/gsm8k/papers/4","list_of":"/task/gsm8k","task":"GSM8K","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":4,"pages_in_order":5,"rows_per_page":100,"rows":[301,400],"of":439,"counts":{"archive_papers_tagged":439,"with_a_code_link":209,"where_syntology_ran_a_sample":116,"not_listed_spam_title":0,"listed":439,"listed_where_code_ran":116,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":96,"every_run_a_failure_of_syntologys_instrument":20,"listed_with_a_run_with_no_instrument_failure":96,"listed_every_run_a_failure_of_syntologys_instrument":20,"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/gsm8k","prev":"/task/gsm8k/papers/3","next":"/task/gsm8k/papers/5","papers":[{"url":null,"slug":"evolutionary-pre-prompt-optimization-for","title":"Evolutionary Pre-Prompt Optimization for Mathematical Reasoning","date":"2024-12-05","arxiv_id":"2412.04291","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-free-mitigation-of-language","title":"Training-Free Mitigation of Language Reasoning Degradation After Multimodal Instruction Tuning","date":"2024-12-04","arxiv_id":"2412.03467","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":"mixture-of-cache-conditional-experts-for","title":"Mixture of Cache-Conditional Experts for Efficient Mobile Device Inference","date":"2024-11-27","arxiv_id":"2412.00099","repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-emergent-capabilities-by","title":"Predicting Emergent Capabilities by Finetuning","date":"2024-11-25","arxiv_id":"2411.16035","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":"patience-is-the-key-to-large-language-model","title":"Patience Is The Key to Large Language Model Reasoning","date":"2024-11-20","arxiv_id":"2411.13082","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-decoding-via-latent-preference","title":"Adaptive Decoding via Latent Preference Optimization","date":"2024-11-14","arxiv_id":"2411.09661","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-subset-tuning-expanding-the","title":"Dynamic Subset Tuning: Expanding the Operational Range of Parameter-Efficient Training for Large Language Models","date":"2024-11-13","arxiv_id":"2411.08610","repositories_listed":0,"syntology":null},{"url":null,"slug":"quasi-random-multi-sample-inference-for-large","title":"Quasi-random Multi-Sample Inference for Large Language Models","date":"2024-11-09","arxiv_id":"2411.06251","repositories_listed":0,"syntology":null},{"url":null,"slug":"reasoning-robustness-of-llms-to-adversarial","title":"Reasoning Robustness of LLMs to Adversarial Typographical Errors","date":"2024-11-08","arxiv_id":"2411.05345","repositories_listed":0,"syntology":null},{"url":null,"slug":"kwai-star-transform-llms-into-state","title":"Kwai-STaR: Transform LLMs into State-Transition Reasoners","date":"2024-11-07","arxiv_id":"2411.04799","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":"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":null,"slug":"rethinking-data-synthesis-a-teacher-model","title":"Rethinking Data Synthesis: A Teacher Model Training Recipe with Interpretation","date":"2024-10-27","arxiv_id":"2410.20362","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":"adaptive-dense-reward-understanding-the-gap","title":"Adaptive Dense Reward: Understanding the Gap Between Action and Reward Space in Alignment","date":"2024-10-23","arxiv_id":"2411.00809","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":"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":"treebon-enhancing-inference-time-alignment","title":"TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling","date":"2024-10-18","arxiv_id":"2410.16033","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":"nudging-inference-time-alignment-via-model","title":"Nudging: Inference-time Alignment of LLMs via Guided Decoding","date":"2024-10-11","arxiv_id":"2410.09300","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-cross-lingual-llm-evaluation-for","title":"Towards Multilingual LLM Evaluation for European Languages","date":"2024-10-11","arxiv_id":"2410.08928","repositories_listed":0,"syntology":null},{"url":null,"slug":"dialectical-behavior-therapy-approach-to-llm","title":"Dialectical Behavior Therapy Approach to LLM Prompting","date":"2024-10-10","arxiv_id":"2410.07768","repositories_listed":0,"syntology":null},{"url":null,"slug":"think-beyond-size-dynamic-prompting-for-more","title":"Think Beyond Size: Adaptive Prompting for More Effective Reasoning","date":"2024-10-10","arxiv_id":"2410.08130","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":"fine-grained-hallucination-detection-and-2","title":"FG-PRM: Fine-grained Hallucination Detection and Mitigation in Language Model Mathematical Reasoning","date":"2024-10-08","arxiv_id":"2410.06304","repositories_listed":0,"syntology":null},{"url":null,"slug":"portllm-personalizing-evolving-large-language","title":"PortLLM: Personalizing Evolving Large Language Models with Training-Free and Portable Model Patches","date":"2024-10-08","arxiv_id":"2410.10870","repositories_listed":0,"syntology":null},{"url":null,"slug":"reasoning-paths-optimization-learning-to","title":"Reasoning Paths Optimization: Learning to Reason and Explore From Diverse Paths","date":"2024-10-07","arxiv_id":"2410.10858","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-llm-reasoning-through-scaling","title":"Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification","date":"2024-10-05","arxiv_id":"2410.05318","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-inference-time-compute-llms-can","title":"Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation","date":"2024-10-03","arxiv_id":"2410.02725","repositories_listed":0,"syntology":null},{"url":null,"slug":"braintransformers-snn-llm","title":"BrainTransformers: SNN-LLM","date":"2024-10-03","arxiv_id":"2410.14687","repositories_listed":0,"syntology":null},{"url":null,"slug":"codepmp-scalable-preference-model-pretraining","title":"CodePMP: Scalable Preference Model Pretraining for Large Language Model Reasoning","date":"2024-10-03","arxiv_id":"2410.02229","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-role-of-deductive-and-inductive-reasoning","title":"The Role of Deductive and Inductive Reasoning in Large Language Models","date":"2024-10-03","arxiv_id":"2410.02892","repositories_listed":0,"syntology":null},{"url":null,"slug":"unlocking-structured-thinking-in-language","title":"Unlocking Structured Thinking in Language Models with Cognitive Prompting","date":"2024-10-03","arxiv_id":"2410.02953","repositories_listed":0,"syntology":null},{"url":null,"slug":"personamath-enhancing-math-reasoning-through","title":"PersonaMath: Enhancing Math Reasoning through Persona-Driven Data Augmentation","date":"2024-10-02","arxiv_id":"2410.01504","repositories_listed":0,"syntology":null},{"url":null,"slug":"instance-adaptive-zero-shot-chain-of-thought","title":"Instance-adaptive Zero-shot Chain-of-Thought Prompting","date":"2024-09-30","arxiv_id":"2409.20441","repositories_listed":0,"syntology":null},{"url":null,"slug":"llama-sciq-an-educational-chatbot-for","title":"LLaMa-SciQ: An Educational Chatbot for Answering Science MCQ","date":"2024-09-25","arxiv_id":"2409.16779","repositories_listed":0,"syntology":null},{"url":null,"slug":"pmss-pretrained-matrices-skeleton-selection","title":"PMSS: Pretrained Matrices Skeleton Selection for LLM Fine-tuning","date":"2024-09-25","arxiv_id":"2409.16722","repositories_listed":0,"syntology":null},{"url":null,"slug":"2409-14026","title":"Uncovering Latent Chain of Thought Vectors in Language Models","date":"2024-09-21","arxiv_id":"2409.14026","repositories_listed":0,"syntology":null},{"url":null,"slug":"controlmath-controllable-data-generation","title":"ControlMath: Controllable Data Generation Promotes Math Generalist Models","date":"2024-09-20","arxiv_id":"2409.15376","repositories_listed":0,"syntology":null},{"url":"/paper/qwen2-5-math-technical-report-toward","slug":"qwen2-5-math-technical-report-toward","title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","date":"2024-09-18","arxiv_id":"2409.12122","repositories_listed":0,"syntology":null},{"url":null,"slug":"cpl-critical-planning-step-learning-boosts","title":"CPL: Critical Plan Step Learning Boosts LLM Generalization in Reasoning Tasks","date":"2024-09-13","arxiv_id":"2409.08642","repositories_listed":0,"syntology":null},{"url":null,"slug":"stun-structured-then-unstructured-pruning-for","title":"STUN: Structured-Then-Unstructured Pruning for Scalable MoE Pruning","date":"2024-09-10","arxiv_id":"2409.06211","repositories_listed":0,"syntology":null},{"url":null,"slug":"strategic-chain-of-thought-guiding-accurate","title":"Strategic Chain-of-Thought: Guiding Accurate Reasoning in LLMs through Strategy Elicitation","date":"2024-09-05","arxiv_id":"2409.03271","repositories_listed":0,"syntology":null},{"url":null,"slug":"building-math-agents-with-multi-turn","title":"Building Math Agents with Multi-Turn Iterative Preference Learning","date":"2024-09-04","arxiv_id":"2409.02392","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-baking","title":"Prompt Baking","date":"2024-09-04","arxiv_id":"2409.13697","repositories_listed":0,"syntology":null},{"url":null,"slug":"s-3-c-math-spontaneous-step-level-self","title":"S$^3$c-Math: Spontaneous Step-level Self-correction Makes Large Language Models Better Mathematical Reasoners","date":"2024-09-03","arxiv_id":"2409.01524","repositories_listed":0,"syntology":null},{"url":null,"slug":"critic-cot-boosting-the-reasoning-abilities","title":"Critic-CoT: Boosting the reasoning abilities of large language model via Chain-of-thoughts Critic","date":"2024-08-29","arxiv_id":"2408.16326","repositories_listed":0,"syntology":null},{"url":null,"slug":"logic-contrastive-reasoning-with-lightweight","title":"Logic Contrastive Reasoning with Lightweight Large Language Model for Math Word Problems","date":"2024-08-29","arxiv_id":"2409.00131","repositories_listed":0,"syntology":null},{"url":null,"slug":"siam-self-improving-code-assisted","title":"SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models","date":"2024-08-28","arxiv_id":"2408.15565","repositories_listed":0,"syntology":null},{"url":null,"slug":"threshold-filtering-packing-for-supervised","title":"Threshold Filtering Packing for Supervised Fine-Tuning: Training Related Samples within Packs","date":"2024-08-18","arxiv_id":"2408.09327","repositories_listed":0,"syntology":null},{"url":null,"slug":"selectllm-query-aware-efficient-selection","title":"SelectLLM: Query-Aware Efficient Selection Algorithm for Large Language Models","date":"2024-08-16","arxiv_id":"2408.08545","repositories_listed":0,"syntology":null},{"url":null,"slug":"concise-thoughts-impact-of-output-length-on","title":"Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost","date":"2024-07-29","arxiv_id":"2407.19825","repositories_listed":0,"syntology":null},{"url":null,"slug":"cool-fusion-fuse-large-language-models","title":"Cool-Fusion: Fuse Large Language Models without Training","date":"2024-07-29","arxiv_id":"2407.19807","repositories_listed":0,"syntology":null},{"url":null,"slug":"reliable-reasoning-beyond-natural-language","title":"Reliable Reasoning Beyond Natural Language","date":"2024-07-16","arxiv_id":"2407.11373","repositories_listed":0,"syntology":null},{"url":null,"slug":"token-supervised-value-models-for-enhancing","title":"Token-Supervised Value Models for Enhancing Mathematical Reasoning Capabilities of Large Language Models","date":"2024-07-12","arxiv_id":"2407.12863","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-your-model-really-a-good-math-reasoner","title":"Is Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with Checklist","date":"2024-07-11","arxiv_id":"2407.08733","repositories_listed":0,"syntology":null},{"url":null,"slug":"skywork-math-data-scaling-laws-for","title":"Skywork-Math: Data Scaling Laws for Mathematical Reasoning in Large Language Models -- The Story Goes On","date":"2024-07-11","arxiv_id":"2407.08348","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-is-the-consistent-prediction-likely-to","title":"When is the consistent prediction likely to be a correct prediction?","date":"2024-07-08","arxiv_id":"2407.05778","repositories_listed":0,"syntology":null},{"url":null,"slug":"question-analysis-prompting-improves-llm","title":"Question-Analysis Prompting Improves LLM Performance in Reasoning Tasks","date":"2024-07-04","arxiv_id":"2407.03624","repositories_listed":0,"syntology":null},{"url":null,"slug":"agentinstruct-toward-generative-teaching-with","title":"AgentInstruct: Toward Generative Teaching with Agentic Flows","date":"2024-07-03","arxiv_id":"2407.03502","repositories_listed":0,"syntology":null},{"url":null,"slug":"min-p-sampling-balancing-creativity-and","title":"Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs","date":"2024-07-01","arxiv_id":"2407.01082","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-process-verification-for-large","title":"Advancing Process Verification for Large Language Models via Tree-Based Preference Learning","date":"2024-06-29","arxiv_id":"2407.00390","repositories_listed":0,"syntology":null},{"url":null,"slug":"litesearch-efficacious-tree-search-for-llm","title":"LiteSearch: Efficacious Tree Search for LLM","date":"2024-06-29","arxiv_id":"2407.00320","repositories_listed":0,"syntology":null},{"url":null,"slug":"port-preference-optimization-on-reasoning","title":"PORT: Preference Optimization on Reasoning Traces","date":"2024-06-23","arxiv_id":"2406.16061","repositories_listed":0,"syntology":null},{"url":null,"slug":"q-improving-multi-step-reasoning-for-llms","title":"Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning","date":"2024-06-20","arxiv_id":"2406.14283","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-aware-learning-for-language-model","title":"Uncertainty Aware Learning for Language Model Alignment","date":"2024-06-07","arxiv_id":"2406.04854","repositories_listed":0,"syntology":null},{"url":null,"slug":"does-your-data-spark-joy-performance-gains","title":"Does your data spark joy? Performance gains from domain upsampling at the end of training","date":"2024-06-05","arxiv_id":"2406.03476","repositories_listed":0,"syntology":null},{"url":null,"slug":"improve-mathematical-reasoning-in-language","title":"Improve Mathematical Reasoning in Language Models by Automated Process Supervision","date":"2024-06-05","arxiv_id":"2406.06592","repositories_listed":0,"syntology":null},{"url":null,"slug":"specdec-boosting-speculative-decoding-via","title":"SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths","date":"2024-05-30","arxiv_id":"2405.19715","repositories_listed":0,"syntology":null},{"url":null,"slug":"arithmetic-reasoning-with-llm-prolog","title":"Arithmetic Reasoning with LLM: Prolog Generation & Permutation","date":"2024-05-28","arxiv_id":"2405.17893","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-reference-preference-optimization-for","title":"Multi-Reference Preference Optimization for Large Language Models","date":"2024-05-26","arxiv_id":"2405.16388","repositories_listed":0,"syntology":null},{"url":null,"slug":"mindstar-enhancing-math-reasoning-in-pre","title":"MindStar: Enhancing Math Reasoning in Pre-trained LLMs at Inference Time","date":"2024-05-25","arxiv_id":"2405.16265","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":"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":"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":"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":"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":"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":null,"slug":"relevant-or-random-can-llms-truly-perform","title":"Relevant or Random: Can LLMs Truly Perform Analogical Reasoning?","date":"2024-04-19","arxiv_id":"2404.12728","repositories_listed":0,"syntology":null},{"url":null,"slug":"reka-core-flash-and-edge-a-series-of-powerful","title":"Reka Core, Flash, and Edge: A Series of Powerful Multimodal Language Models","date":"2024-04-18","arxiv_id":"2404.12387","repositories_listed":0,"syntology":null},{"url":null,"slug":"treacle-thrifty-reasoning-via-context-aware","title":"Efficient Contextual LLM Cascades through Budget-Constrained Policy Learning","date":"2024-04-17","arxiv_id":"2404.13082","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-prompt-selection-for-large-language","title":"Automatic Prompt Selection for Large Language Models","date":"2024-04-03","arxiv_id":"2404.02717","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-saw-leveraging-relation-aware-graphs","title":"Prompt-SAW: Leveraging Relation-Aware Graphs for Textual Prompt Compression","date":"2024-03-30","arxiv_id":"2404.00489","repositories_listed":0,"syntology":null},{"url":null,"slug":"supervisory-prompt-training","title":"Supervisory Prompt Training","date":"2024-03-26","arxiv_id":"2403.18051","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":"prompt-selection-and-augmentation-for-few","title":"Prompt Selection and Augmentation for Few Examples Code Generation in Large Language Model and its Application in Robotics Control","date":"2024-03-11","arxiv_id":"2403.12999","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":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":"look-before-you-leap-problem-elaboration","title":"Look Before You Leap: Problem Elaboration Prompting Improves Mathematical Reasoning in Large Language Models","date":"2024-02-24","arxiv_id":"2402.15764","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-self-endorsement-improves","title":"Fine-Grained Self-Endorsement Improves Factuality and Reasoning","date":"2024-02-23","arxiv_id":"2402.15631","repositories_listed":0,"syntology":null},{"url":null,"slug":"symba-symbolic-backward-chaining-for-multi","title":"SymBa: Symbolic Backward Chaining for Structured Natural Language Reasoning","date":"2024-02-20","arxiv_id":"2402.12806","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-separators-improve-chain-of-thought","title":"Can Separators Improve Chain-of-Thought Prompting?","date":"2024-02-16","arxiv_id":"2402.10645","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":"premise-order-matters-in-reasoning-with-large","title":"Premise Order Matters in Reasoning with Large Language Models","date":"2024-02-14","arxiv_id":"2402.08939","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":"/paper/the-unreasonable-effectiveness-of-eccentric","slug":"the-unreasonable-effectiveness-of-eccentric","title":"The Unreasonable Effectiveness of Eccentric Automatic Prompts","date":"2024-02-09","arxiv_id":"2402.10949","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}],"record_sha256":"6be1eecd4cf013a215322130fa631e8d79de9bc306ec90895eea829c0ac0a10d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}