{"total":133,"rows":[{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459,"area":"lr"},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708,"area":"lr"},{"id":"2203.10244","title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","created":"2022-03-19","cited_by_count":1479,"area":"lr"},{"id":"2211.10435","title":"PAL: Program-aided Language Models","created":"2022-11-18","cited_by_count":652,"area":"lr"},{"id":"2102.01017","title":"Measuring and Improving Consistency in Pretrained Language Models","created":"2021-02-01","cited_by_count":364,"area":null},{"id":"2206.02336","title":"Making Large Language Models Better Reasoners with Step-Aware Verifier","created":"2022-06-06","cited_by_count":233,"area":"lr"},{"id":"2304.01904","title":"REFINER: Reasoning Feedback on Intermediate Representations","created":"2023-04-04","cited_by_count":205,"area":"lr"},{"id":"2305.00586","title":"How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model","created":"2023-04-30","cited_by_count":202,"area":null},{"id":"2301.04883","title":"SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images","created":"2023-01-12","cited_by_count":179,"area":null},{"id":"2202.07206","title":"Impact of Pretraining Term Frequencies on Few-Shot Reasoning","created":"2022-02-15","cited_by_count":142,"area":"lr"},{"id":"2204.07580","title":"mGPT: Few-Shot Learners Go Multilingual","created":"2022-04-15","cited_by_count":142,"area":null},{"id":"2102.13019","title":"Investigating the Limitations of Transformers with Simple Arithmetic Tasks","created":"2021-02-25","cited_by_count":139,"area":null},{"id":"2212.09662","title":"MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering","created":"2022-12-19","cited_by_count":133,"area":"lr"},{"id":"2212.10535","title":"A Survey of Deep Learning for Mathematical Reasoning","created":"2022-12-20","cited_by_count":124,"area":"lr"},{"id":"2206.01347","title":"MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Data","created":"2022-06-03","cited_by_count":121,"area":null},{"id":"2206.00426","title":"Semantic Probabilistic Layers for Neuro-Symbolic Learning","created":"2022-06-01","cited_by_count":103,"area":null},{"id":"2406.10833","title":"A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery","created":"2024-06-16","cited_by_count":96,"area":null},{"id":"2103.13136","title":"Representing Numbers in NLP: a Survey and a Vision","created":"2021-03-24","cited_by_count":83,"area":null},{"id":"2210.12023","title":"A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models","created":"2022-10-21","cited_by_count":68,"area":"lr"},{"id":"2204.08831","title":"Probing for the Usage of Grammatical Number","created":"2022-04-19","cited_by_count":59,"area":null},{"id":"2106.04571","title":"TIMEDIAL: Temporal Commonsense Reasoning in Dialog","created":"2021-06-08","cited_by_count":55,"area":null},{"id":"2205.12586","title":"Perturbation Augmentation for Fairer NLP","created":"2022-05-25","cited_by_count":52,"area":null},{"id":"2203.06482","title":"FiNER: Financial Numeric Entity Recognition for XBRL Tagging","created":"2022-03-12","cited_by_count":50,"area":null},{"id":"2310.02227","title":"SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training","created":"2023-10-03","cited_by_count":47,"area":null},{"id":"2201.11473","title":"Reasoning Like Program Executors","created":"2022-01-27","cited_by_count":45,"area":"lr"},{"id":"2210.08817","title":"PACIFIC: Towards Proactive Conversational Question Answering over Tabular and Textual Data in Finance","created":"2022-10-17","cited_by_count":45,"area":null},{"id":"2411.03766","title":"Number Cookbook: Number Understanding of Language Models and How to Improve It","created":"2024-11-06","cited_by_count":42,"area":null},{"id":"2107.07261","title":"Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skills","created":"2021-07-15","cited_by_count":39,"area":null},{"id":"2201.12438","title":"Commonsense Knowledge Reasoning and Generation with Pre-trained Language Models: A Survey","created":"2022-01-28","cited_by_count":38,"area":null},{"id":"2104.01785","title":"Annotating Columns with Pre-trained Language Models","created":"2021-04-05","cited_by_count":37,"area":null},{"id":"2109.05644","title":"SHAPE: Shifted Absolute Position Embedding for Transformers","created":"2021-09-13","cited_by_count":37,"area":null},{"id":"2107.13435","title":"MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem Solving","created":"2021-07-28","cited_by_count":32,"area":null},{"id":"2210.12374","title":"ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples","created":"2022-10-22","cited_by_count":29,"area":"lr"},{"id":"2310.14029","title":"LLM-Prop: Predicting Physical And Electronic Properties Of Crystalline Solids From Their Text Descriptions","created":"2023-10-21","cited_by_count":29,"area":null},{"id":"2312.07622","title":"Mathematical Language Models: A Survey","created":"2023-12-12","cited_by_count":24,"area":null},{"id":"2106.03921","title":"Measuring and Improving BERT's Mathematical Abilities by Predicting the Order of Reasoning","created":"2021-06-07","cited_by_count":23,"area":null},{"id":"2109.07323","title":"FORTAP: Using Formulas for Numerical-Reasoning-Aware Table Pretraining","created":"2021-09-15","cited_by_count":19,"area":null},{"id":"2303.07735","title":"Can neural networks do arithmetic? A survey on the elementary numerical skills of state-of-the-art deep learning models","created":"2023-03-14","cited_by_count":18,"area":"lr"},{"id":"2107.01641","title":"A Theoretical Analysis of Fine-tuning with Linear Teachers","created":"2021-07-04","cited_by_count":17,"area":null},{"id":"2108.06743","title":"Exploring Generalization Ability of Pretrained Language Models on Arithmetic and Logical Reasoning","created":"2021-08-15","cited_by_count":17,"area":null},{"id":"2409.01281","title":"Path-Consistency with Prefix Enhancement for Efficient Inference in LLMs","created":"2024-08-25","cited_by_count":17,"area":"lr"},{"id":"2104.08620","title":"Decrypting Cryptic Crosswords: Semantically Complex Wordplay Puzzles as a Target for NLP","created":"2021-04-17","cited_by_count":16,"area":null},{"id":"2212.09897","title":"Inducing Character-level Structure in Subword-based Language Models with Type-level Interchange Intervention Training","created":"2022-12-19","cited_by_count":16,"area":null},{"id":"2109.02102","title":"Teaching Autoregressive Language Models Complex Tasks By Demonstration","created":"2021-09-05","cited_by_count":15,"area":null},{"id":"2109.03137","title":"NumGPT: Improving Numeracy Ability of Generative Pre-trained Models","created":"2021-09-07","cited_by_count":15,"area":null},{"id":"2304.10977","title":"Evaluating Transformer Language Models on Arithmetic Operations Using Number Decomposition","created":"2023-04-21","cited_by_count":15,"area":null},{"id":"2104.01099","title":"TAPAS at SemEval-2021 Task 9: Reasoning over tables with intermediate pre-training","created":"2021-04-02","cited_by_count":14,"area":null},{"id":"2210.10105","title":"ELASTIC: Numerical Reasoning with Adaptive Symbolic Compiler","created":"2022-10-18","cited_by_count":14,"area":"lr"},{"id":"2304.07995","title":"From Zero to Hero: Examining the Power of Symbolic Tasks in Instruction Tuning","created":"2023-04-17","cited_by_count":14,"area":null},{"id":"2109.04672","title":"Investigating Numeracy Learning Ability of a Text-to-Text Transfer Model","created":"2021-09-10","cited_by_count":13,"area":null},{"id":"2203.10581","title":"Cluster & Tune: Boost Cold Start Performance in Text Classification","created":"2022-03-20","cited_by_count":13,"area":null},{"id":"2210.08249","title":"UniRPG: Unified Discrete Reasoning over Table and Text as Program Generation","created":"2022-10-15","cited_by_count":13,"area":null},{"id":"2401.08664","title":"Adapting Large Language Models for Education: Foundational Capabilities, Potentials, and Challenges","created":"2023-12-27","cited_by_count":13,"area":null},{"id":"2411.02083","title":"Regress, Don't Guess -- A Regression-like Loss on Number Tokens for Language Models","created":"2024-11-04","cited_by_count":13,"area":null},{"id":"2107.09852","title":"CausalBERT: Injecting Causal Knowledge Into Pre-trained Models with Minimal Supervision","created":"2021-07-21","cited_by_count":12,"area":null},{"id":"2304.01665","title":"Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural Networks","created":"2023-04-04","cited_by_count":12,"area":"lr"},{"id":"2306.01707","title":"Learning Multi-Step Reasoning by Solving Arithmetic Tasks","created":"2023-06-02","cited_by_count":12,"area":"lr"},{"id":"2309.05452","title":"Evaluating the Deductive Competence of Large Language Models","created":"2023-09-11","cited_by_count":12,"area":null},{"id":"2503.17726","title":"A Survey on Mathematical Reasoning and Optimization with Large Language Models","created":"2025-03-22","cited_by_count":12,"area":"lr"},{"id":"2104.07307","title":"NT5?! Training T5 to Perform Numerical Reasoning","created":"2021-04-15","cited_by_count":11,"area":null},{"id":"2205.08794","title":"LogiGAN: Learning Logical Reasoning via Adversarial Pre-training","created":"2022-05-18","cited_by_count":11,"area":"lr"},{"id":"2302.07866","title":"Do Deep Neural Networks Capture Compositionality in Arithmetic Reasoning?","created":"2023-02-15","cited_by_count":11,"area":"lr"},{"id":"2406.01895","title":"Explicitly Encoding Structural Symmetry is Key to Length Generalization in Arithmetic Tasks","created":"2024-06-04","cited_by_count":11,"area":"lr"},{"id":"2101.11802","title":"Weakly Supervised Neuro-Symbolic Module Networks for Numerical Reasoning","created":"2021-01-28","cited_by_count":10,"area":null},{"id":"2207.12571","title":"Innovations in Neural Data-to-text Generation: A Survey","created":"2022-07-25","cited_by_count":10,"area":null},{"id":"2208.11445","title":"Induced Natural Language Rationales and Interleaved Markup Tokens Enable Extrapolation in Large Language Models","created":"2022-08-24","cited_by_count":10,"area":null},{"id":"2305.10782","title":"Human Behavioral Benchmarking: Numeric Magnitude Comparison Effects in Large Language Models","created":"2023-05-18","cited_by_count":10,"area":null},{"id":"2104.06129","title":"What's in your Head? Emergent Behaviour in Multi-Task Transformer Models","created":"2021-04-13","cited_by_count":9,"area":null},{"id":"2109.08207","title":"Numerical reasoning in machine reading comprehension tasks: are we there yet?","created":"2021-09-16","cited_by_count":9,"area":null},{"id":"2204.10615","title":"Generalized Quantifiers as a Source of Error in Multilingual NLU Benchmarks","created":"2022-04-22","cited_by_count":8,"area":null},{"id":"2402.10979","title":"SportsMetrics: Blending Text and Numerical Data to Understand Information Fusion in LLMs","created":"2024-02-15","cited_by_count":8,"area":null},{"id":"2408.05141","title":"A Hybrid RAG System with Comprehensive Enhancement on Complex Reasoning","created":"2024-08-09","cited_by_count":8,"area":"lr"},{"id":"2509.10739","title":"Reasoning Under Uncertainty: Exploring Probabilistic Reasoning Capabilities of LLMs","created":"2025-09-12","cited_by_count":8,"area":"lr"},{"id":"2110.01509","title":"DeepA2: A Modular Framework for Deep Argument Analysis with Pretrained Neural Text2Text Language Models","created":"2021-10-04","cited_by_count":7,"area":null},{"id":"2204.14166","title":"OPERA:Operation-Pivoted Discrete Reasoning over Text","created":"2022-04-29","cited_by_count":7,"area":null},{"id":"2205.12496","title":"Teaching Broad Reasoning Skills for Multi-Step QA by Generating Hard Contexts","created":"2022-05-25","cited_by_count":7,"area":"lr"},{"id":"2207.02536","title":"Transformers discover an elementary calculation system exploiting local attention and grid-like problem representation","created":"2022-07-06","cited_by_count":7,"area":"lr"},{"id":"2210.05075","title":"Reflection of Thought: Inversely Eliciting Numerical Reasoning in Language Models via Solving Linear Systems","created":"2022-10-11","cited_by_count":7,"area":"lr"},{"id":"2212.09912","title":"Tokenization Consistency Matters for Generative Models on Extractive NLP Tasks","created":"2022-12-19","cited_by_count":7,"area":null},{"id":"2305.12544","title":"Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models","created":"2023-05-21","cited_by_count":7,"area":null},{"id":"2403.11413","title":"Dynamic Contexts for Generating Suggestion Questions in RAG Based Conversational Systems","created":"2024-03-18","cited_by_count":7,"area":"rag"},{"id":"2506.09677","title":"Benchmarking Gaslighting Negation Attacks Against Reasoning Models","created":"2025-06-11","cited_by_count":6,"area":"lr"},{"id":"2112.08616","title":"Masked Measurement Prediction: Learning to Jointly Predict Quantities and Units from Textual Context","created":"2021-12-16","cited_by_count":5,"area":null},{"id":"2305.08246","title":"Learning Non-linguistic Skills without Sacrificing Linguistic Proficiency","created":"2023-05-14","cited_by_count":5,"area":"lr"},{"id":"2402.16905","title":"Procedural Adherence and Interpretability Through Neuro-Symbolic Generative Agents","created":"2024-02-24","cited_by_count":5,"area":"agents"},{"id":"2407.00894","title":"How to Leverage Digit Embeddings to Represent Numbers?","created":"2024-07-01","cited_by_count":5,"area":null},{"id":"2503.13992","title":"The KoLMogorov Test: Compression by Code Generation","created":"2025-03-18","cited_by_count":5,"area":null},{"id":"2112.06109","title":"Injecting Numerical Reasoning Skills into Knowledge Base Question Answering Models","created":"2021-12-12","cited_by_count":4,"area":null},{"id":"2201.09651","title":"Artefact Retrieval: Overview of NLP Models with Knowledge Base Access","created":"2022-01-24","cited_by_count":4,"area":null},{"id":"2211.02098","title":"Overcoming Barriers to Skill Injection in Language Modeling: Case Study in Arithmetic","created":"2022-11-03","cited_by_count":4,"area":null},{"id":"2211.03462","title":"NAPG: Non-Autoregressive Program Generation for Hybrid Tabular-Textual Question Answering","created":"2022-11-07","cited_by_count":4,"area":null},{"id":"2301.08913","title":"Unifying Structure Reasoning and Language Model Pre-training for Complex Reasoning","created":"2023-01-21","cited_by_count":4,"area":"lr"},{"id":"2205.06733","title":"Arithmetic-Based Pretraining -- Improving Numeracy of Pretrained Language Models","created":"2022-05-13","cited_by_count":3,"area":null},{"id":"2211.12641","title":"Leveraging Data Recasting to Enhance Tabular Reasoning","created":"2022-11-23","cited_by_count":3,"area":null},{"id":"2301.06758","title":"Tracing and Manipulating Intermediate Values in Neural Math Problem Solvers","created":"2023-01-17","cited_by_count":3,"area":null},{"id":"2305.11826","title":"ReTAG: Reasoning Aware Table to Analytic Text Generation","created":"2023-05-19","cited_by_count":3,"area":null},{"id":"2305.17491","title":"FERMAT: An Alternative to Accuracy for Numerical Reasoning","created":"2023-05-27","cited_by_count":3,"area":"lr"},{"id":"2310.18371","title":"In-Context Ability Transfer for Question Decomposition in Complex QA","created":"2023-10-26","cited_by_count":3,"area":null},{"id":"2604.04944","title":"Inclusion-of-Thoughts: Mitigating Preference Instability via Purifying the Decision Space","created":"2026-03-15","cited_by_count":3,"area":"lr"},{"id":"2108.07994","title":"EviDR: Evidence-Emphasized Discrete Reasoning for Reasoning Machine Reading Comprehension","created":"2021-08-18","cited_by_count":2,"area":null}],"next_cursor":"100"}