{"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/logical-reasoning/papers/5","list_of":"/task/logical-reasoning","task":"Logical Reasoning","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":5,"pages_in_order":8,"rows_per_page":100,"rows":[401,500],"of":747,"counts":{"archive_papers_tagged":747,"with_a_code_link":330,"where_syntology_ran_a_sample":113,"not_listed_spam_title":0,"listed":747,"listed_where_code_ran":113,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":96,"every_run_a_failure_of_syntologys_instrument":17,"listed_with_a_run_with_no_instrument_failure":96,"listed_every_run_a_failure_of_syntologys_instrument":17,"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/logical-reasoning","prev":"/task/logical-reasoning/papers/4","next":"/task/logical-reasoning/papers/6","papers":[{"url":null,"slug":"sppd-self-training-with-process-preference","title":"SPPD: Self-training with Process Preference Learning Using Dynamic Value Margin","date":"2025-02-19","arxiv_id":"2502.13516","repositories_listed":0,"syntology":null},{"url":null,"slug":"hoprag-multi-hop-reasoning-for-logic-aware","title":"HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation","date":"2025-02-18","arxiv_id":"2502.12442","repositories_listed":0,"syntology":null},{"url":null,"slug":"inference-time-computations-for-llm-reasoning","title":"Inference-Time Computations for LLM Reasoning and Planning: A Benchmark and Insights","date":"2025-02-18","arxiv_id":"2502.12521","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-large-language-models-to-be-better","title":"Beyond Single-Task: Robust Multi-Task Length Generalization for LLMs","date":"2025-02-17","arxiv_id":"2502.11525","repositories_listed":0,"syntology":null},{"url":null,"slug":"dialogue-based-explanations-for-logical","title":"Dialogue-based Explanations for Logical Reasoning using Structured Argumentation","date":"2025-02-16","arxiv_id":"2502.11291","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantifying-the-capability-boundary-of","title":"Quantifying the Capability Boundary of DeepSeek Models: An Application-Driven Performance Analysis","date":"2025-02-16","arxiv_id":"2502.11164","repositories_listed":0,"syntology":null},{"url":null,"slug":"logical-forms-complement-probability-in","title":"Logical forms complement probability in understanding language model (and human) performance","date":"2025-02-13","arxiv_id":"2502.09589","repositories_listed":0,"syntology":null},{"url":null,"slug":"logical-lease-litigation-prolog-and-llms-for","title":"Logical Lease Litigation: Prolog and LLMs for Rental Law Compliance in New York","date":"2025-02-13","arxiv_id":"2502.09204","repositories_listed":0,"syntology":null},{"url":null,"slug":"logical-reasoning-in-large-language-models-a","title":"Logical Reasoning in Large Language Models: A Survey","date":"2025-02-13","arxiv_id":"2502.09100","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-multilingual-mind-a-survey-of","title":"The Multilingual Mind : A Survey of Multilingual Reasoning in Language Models","date":"2025-02-13","arxiv_id":"2502.09457","repositories_listed":0,"syntology":null},{"url":null,"slug":"dmwm-dual-mind-world-model-with-long-term","title":"DMWM: Dual-Mind World Model with Long-Term Imagination","date":"2025-02-11","arxiv_id":"2502.07591","repositories_listed":0,"syntology":null},{"url":null,"slug":"structural-reformation-of-large-language","title":"Structural Reformation of Large Language Model Neuron Encapsulation for Divergent Information Aggregation","date":"2025-02-10","arxiv_id":"2502.07124","repositories_listed":0,"syntology":null},{"url":null,"slug":"s-2-mad-breaking-the-token-barrier-to-enhance","title":"S$^2$-MAD: Breaking the Token Barrier to Enhance Multi-Agent Debate Efficiency","date":"2025-02-07","arxiv_id":"2502.04790","repositories_listed":0,"syntology":null},{"url":null,"slug":"symagent-a-neural-symbolic-self-learning","title":"SymAgent: A Neural-Symbolic Self-Learning Agent Framework for Complex Reasoning over Knowledge Graphs","date":"2025-02-05","arxiv_id":"2502.03283","repositories_listed":0,"syntology":null},{"url":null,"slug":"automating-mathematical-proof-generation","title":"Automating Mathematical Proof Generation Using Large Language Model Agents and Knowledge Graphs","date":"2025-02-04","arxiv_id":"2503.11657","repositories_listed":0,"syntology":null},{"url":null,"slug":"standard-neural-computation-alone-is","title":"Standard Neural Computation Alone Is Insufficient for Logical Intelligence","date":"2025-02-04","arxiv_id":"2502.02135","repositories_listed":0,"syntology":null},{"url":null,"slug":"zebralogic-on-the-scaling-limits-of-llms-for","title":"ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning","date":"2025-02-03","arxiv_id":"2502.01100","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-large-language-model-efficiencyvia","title":"Enhancing Large Language Model Efficiencyvia Symbolic Compression: A Formal Approach Towards Interpretability","date":"2025-01-30","arxiv_id":"2501.18657","repositories_listed":0,"syntology":null},{"url":null,"slug":"instantiation-based-formalization-of-logical","title":"Instantiation-based Formalization of Logical Reasoning Tasks using Language Models and Logical Solvers","date":"2025-01-28","arxiv_id":"2501.16961","repositories_listed":0,"syntology":null},{"url":null,"slug":"town-hall-debate-prompting-enhancing-logical","title":"Town Hall Debate Prompting: Enhancing Logical Reasoning in LLMs through Multi-Persona Interaction","date":"2025-01-28","arxiv_id":"2502.15725","repositories_listed":0,"syntology":null},{"url":null,"slug":"dbrouting-routing-end-user-queries-to","title":"DBRouting: Routing End User Queries to Databases for Answerability","date":"2025-01-27","arxiv_id":"2501.16220","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-causality-aware-paradigm-for-evaluating","title":"A Causality-aware Paradigm for Evaluating Creativity of Multimodal Large Language Models","date":"2025-01-25","arxiv_id":"2501.15147","repositories_listed":0,"syntology":null},{"url":null,"slug":"verus-lm-a-versatile-framework-for-combining","title":"VERUS-LM: a Versatile Framework for Combining LLMs with Symbolic Reasoning","date":"2025-01-24","arxiv_id":"2501.14540","repositories_listed":0,"syntology":null},{"url":null,"slug":"reasoning-with-graphs-structuring-implicit","title":"Reasoning with Graphs: Structuring Implicit Knowledge to Enhance LLMs Reasoning","date":"2025-01-14","arxiv_id":"2501.07845","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-probabilistic-circuits-enabling","title":"Neural Probabilistic Circuits: Enabling Compositional and Interpretable Predictions through Logical Reasoning","date":"2025-01-13","arxiv_id":"2501.07021","repositories_listed":0,"syntology":null},{"url":null,"slug":"timelogic-a-temporal-logic-benchmark-for","title":"TimeLogic: A Temporal Logic Benchmark for Video QA","date":"2025-01-13","arxiv_id":"2501.07214","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-to-text-prompt-engineering-in","title":"Multimodal-to-Text Prompt Engineering in Large Language Models Using Feature Embeddings for GNSS Interference Characterization","date":"2025-01-09","arxiv_id":"2501.05079","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-transformers-for-generalizable","title":"Enhancing Transformers for Generalizable First-Order Logical Entailment","date":"2025-01-01","arxiv_id":"2501.00759","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowra-knowledge-retrieval-augmented-method","title":"KnowRA: Knowledge Retrieval Augmented Method for Document-level Relation Extraction with Comprehensive Reasoning Abilities","date":"2024-12-31","arxiv_id":"2501.00571","repositories_listed":0,"syntology":null},{"url":null,"slug":"secbench-a-comprehensive-multi-dimensional","title":"SecBench: A Comprehensive Multi-Dimensional Benchmarking Dataset for LLMs in Cybersecurity","date":"2024-12-30","arxiv_id":"2412.20787","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":"aristotle-mastering-logical-reasoning-with-a","title":"Aristotle: Mastering Logical Reasoning with A Logic-Complete Decompose-Search-Resolve Framework","date":"2024-12-22","arxiv_id":"2412.16953","repositories_listed":0,"syntology":null},{"url":null,"slug":"formal-language-knowledge-corpus-for","title":"Formal Language Knowledge Corpus for Retrieval Augmented Generation","date":"2024-12-21","arxiv_id":"2412.16689","repositories_listed":0,"syntology":null},{"url":null,"slug":"logical-consistency-of-large-language-models","title":"Logical Consistency of Large Language Models in Fact-checking","date":"2024-12-20","arxiv_id":"2412.16100","repositories_listed":0,"syntology":null},{"url":null,"slug":"reasoning-aware-query-focused-summarization","title":"Reasoning-Aware Query-Focused Summarization over Multi-Table Data","date":"2024-12-12","arxiv_id":"2412.08970","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-in-context-llm-agent-learning","title":"Federated In-Context LLM Agent Learning","date":"2024-12-11","arxiv_id":"2412.08054","repositories_listed":0,"syntology":null},{"url":null,"slug":"algorithmic-phase-transitions-in-language","title":"Algorithmic Phase Transitions in Language Models: A Mechanistic Case Study of Arithmetic","date":"2024-12-10","arxiv_id":"2412.07386","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-openai-o1-outperform-humans-in-higher","title":"Can OpenAI o1 outperform humans in higher-order cognitive thinking?","date":"2024-12-07","arxiv_id":"2412.05753","repositories_listed":0,"syntology":null},{"url":null,"slug":"guidance-is-all-you-need-temperature-guided","title":"Guidance is All You Need: Temperature-Guided Reasoning in Large Language Models","date":"2024-12-05","arxiv_id":"2412.06822","repositories_listed":0,"syntology":null},{"url":null,"slug":"mtmt-consolidating-multiple-thinking-modes-to","title":"MTMT: Consolidating Multiple Thinking Modes to Form a Thought Tree for Strengthening LLM","date":"2024-12-05","arxiv_id":"2412.03987","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-pipeline-of-neural-symbolic-integration-to","title":"Dspy-based Neural-Symbolic Pipeline to Enhance Spatial Reasoning in LLMs","date":"2024-11-27","arxiv_id":"2411.18564","repositories_listed":0,"syntology":null},{"url":null,"slug":"sentixrl-an-advanced-large-language-model","title":"SentiXRL: An advanced large language Model Framework for Multilingual Fine-Grained Emotion Classification in Complex Text Environment","date":"2024-11-27","arxiv_id":"2411.18162","repositories_listed":0,"syntology":null},{"url":null,"slug":"heie-mllm-based-hierarchical-explainable-aigc","title":"HEIE: MLLM-Based Hierarchical Explainable AIGC Image Implausibility Evaluator","date":"2024-11-26","arxiv_id":"2411.17261","repositories_listed":0,"syntology":null},{"url":null,"slug":"meaningless-is-better-hashing-bias-inducing","title":"Meaningless is better: hashing bias-inducing words in LLM prompts improves performance in logical reasoning and statistical learning","date":"2024-11-26","arxiv_id":"2411.17304","repositories_listed":0,"syntology":null},{"url":null,"slug":"interactive-visual-assessment-for-text-to","title":"Interactive Visual Assessment for Text-to-Image Generation Models","date":"2024-11-23","arxiv_id":"2411.15509","repositories_listed":0,"syntology":null},{"url":null,"slug":"xagents-a-framework-for-interpretable-rule","title":"XAgents: A Framework for Interpretable Rule-Based Multi-Agents Cooperation","date":"2024-11-21","arxiv_id":"2411.13932","repositories_listed":0,"syntology":null},{"url":null,"slug":"testing-uncertainty-of-large-language-models","title":"Testing Uncertainty of Large Language Models for Physics Knowledge and Reasoning","date":"2024-11-18","arxiv_id":"2411.14465","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-llms-as-traffic-control","title":"Large Language Models (LLMs) as Traffic Control Systems at Urban Intersections: A New Paradigm","date":"2024-11-16","arxiv_id":"2411.10869","repositories_listed":0,"syntology":null},{"url":null,"slug":"building-trustworthy-ai-transparent-ai","title":"Building Trustworthy AI: Transparent AI Systems via Large Language Models, Ontologies, and Logical Reasoning (TranspNet)","date":"2024-11-13","arxiv_id":"2411.08469","repositories_listed":0,"syntology":null},{"url":null,"slug":"symbolic-ai-fusion-deep-learning-saif-dl","title":"Symbolic-AI-Fusion Deep Learning (SAIF-DL): Encoding Knowledge into Training with Answer Set Programming Loss Penalties by a Novel Loss Function Approach","date":"2024-11-13","arxiv_id":"2411.08463","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-authoring-with-factual-english-1","title":"Knowledge Authoring with Factual English, Rules, and Actions","date":"2024-11-09","arxiv_id":"2411.06253","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":"how-transformers-solve-propositional-logic","title":"How Transformers Solve Propositional Logic Problems: A Mechanistic Analysis","date":"2024-11-06","arxiv_id":"2411.04105","repositories_listed":0,"syntology":null},{"url":null,"slug":"formal-logic-guided-robust-federated-learning","title":"Formal Logic-guided Robust Federated Learning against Poisoning Attacks","date":"2024-11-05","arxiv_id":"2411.03231","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-memorization-of-large-language-models-in","title":"On Memorization of Large Language Models in Logical Reasoning","date":"2024-10-30","arxiv_id":"2410.23123","repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-domain-specific-models-and-llms-for","title":"Combining Domain-Specific Models and LLMs for Automated Disease Phenotyping from Survey Data","date":"2024-10-28","arxiv_id":"2410.20695","repositories_listed":0,"syntology":null},{"url":null,"slug":"reasoning-or-a-semblance-of-it-a-diagnostic","title":"Reasoning or a Semblance of it? A Diagnostic Study of Transitive Reasoning in LLMs","date":"2024-10-26","arxiv_id":"2410.20200","repositories_listed":0,"syntology":null},{"url":null,"slug":"aligning-codellms-with-direct-preference","title":"Aligning CodeLLMs with Direct Preference Optimization","date":"2024-10-24","arxiv_id":"2410.18585","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-small-scale-large-language-models","title":"Improving Small-Scale Large Language Models Function Calling for Reasoning Tasks","date":"2024-10-24","arxiv_id":"2410.18890","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-aided-efficient-hardware-design","title":"LLM-Aided Efficient Hardware Design Automation","date":"2024-10-24","arxiv_id":"2410.18582","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":"exploiting-llms-reasoning-capability-to-infer","title":"Exploiting LLMs' Reasoning Capability to Infer Implicit Concepts in Legal Information Retrieval","date":"2024-10-16","arxiv_id":"2410.12154","repositories_listed":0,"syntology":null},{"url":null,"slug":"let-s-argue-both-sides-argument-generation","title":"\"Let's Argue Both Sides\": Argument Generation Can Force Small Models to Utilize Previously Inaccessible Reasoning Capabilities","date":"2024-10-16","arxiv_id":"2410.12997","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-deductive-reasoning-with-step","title":"Boosting Deductive Reasoning with Step Signals In RLHF","date":"2024-10-12","arxiv_id":"2410.09528","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-based-language-models-for-1","title":"Transformer-based Language Models for Reasoning in the Description Logic ALCQ","date":"2024-10-12","arxiv_id":"2410.09613","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-systematic-assessment-of-openai-o1-preview","title":"A Systematic Assessment of OpenAI o1-Preview for Higher Order Thinking in Education","date":"2024-10-11","arxiv_id":"2410.21287","repositories_listed":0,"syntology":null},{"url":null,"slug":"forall-uto-exists-lor-land-l-autonomous","title":"$\\forall$uto$\\exists$$\\lor\\!\\land$L: Autonomous Evaluation of LLMs for Truth Maintenance and Reasoning Tasks","date":"2024-10-11","arxiv_id":"2410.08437","repositories_listed":0,"syntology":null},{"url":null,"slug":"p-folio-evaluating-and-improving-logical","title":"P-FOLIO: Evaluating and Improving Logical Reasoning with Abundant Human-Written Reasoning Chains","date":"2024-10-11","arxiv_id":"2410.09207","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowgraph-knowledge-enabled-anomaly-detection","title":"KnowGraph: Knowledge-Enabled Anomaly Detection via Logical Reasoning on Graph Data","date":"2024-10-10","arxiv_id":"2410.08390","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":"can-transformers-reason-logically-a-study-in","title":"Can Transformers Reason Logically? A Study in SAT Solving","date":"2024-10-09","arxiv_id":"2410.07432","repositories_listed":0,"syntology":null},{"url":null,"slug":"latent-feature-mining-for-predictive-model","title":"Latent Feature Mining for Predictive Model Enhancement with Large Language Models","date":"2024-10-06","arxiv_id":"2410.04347","repositories_listed":0,"syntology":null},{"url":null,"slug":"deliberate-reasoning-for-llms-as-structure","title":"Deliberate Reasoning for LLMs as Structure-aware Planning with Accurate World Model","date":"2024-10-04","arxiv_id":"2410.03136","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":"graphic-a-graph-based-in-context-example","title":"GraphIC: A Graph-Based In-Context Example Retrieval Model for Multi-Step Reasoning","date":"2024-10-03","arxiv_id":"2410.02203","repositories_listed":0,"syntology":null},{"url":null,"slug":"wait-but-tylenol-is-acetaminophen","title":"Wait, but Tylenol is Acetaminophen... Investigating and Improving Language Models' Ability to Resist Requests for Misinformation","date":"2024-09-30","arxiv_id":"2409.20385","repositories_listed":0,"syntology":null},{"url":null,"slug":"judgment-of-thoughts-courtroom-of-the-binary","title":"Judgment of Thoughts: Courtroom of the Binary Logical Reasoning in Large Language Models","date":"2024-09-25","arxiv_id":"2409.16635","repositories_listed":0,"syntology":null},{"url":null,"slug":"2409-14051","title":"GroupDebate: Enhancing the Efficiency of Multi-Agent Debate Using Group Discussion","date":"2024-09-21","arxiv_id":"2409.14051","repositories_listed":0,"syntology":null},{"url":null,"slug":"proslm-a-prolog-synergized-language-model-for","title":"ProSLM : A Prolog Synergized Language Model for explainable Domain Specific Knowledge Based Question Answering","date":"2024-09-17","arxiv_id":"2409.11589","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-token-sparsification-for-efficient","title":"Video Token Sparsification for Efficient Multimodal LLMs in Autonomous Driving","date":"2024-09-16","arxiv_id":"2409.11182","repositories_listed":0,"syntology":null},{"url":null,"slug":"unleash-llms-potential-for-recommendation-by","title":"Unleash LLMs Potential for Recommendation by Coordinating Twin-Tower Dynamic Semantic Token Generator","date":"2024-09-14","arxiv_id":"2409.09253","repositories_listed":0,"syntology":null},{"url":null,"slug":"causejudger-identifying-the-cause-with-llms","title":"CauseJudger: Identifying the Cause with LLMs for Abductive Logical Reasoning","date":"2024-09-09","arxiv_id":"2409.05559","repositories_listed":0,"syntology":null},{"url":null,"slug":"kargen-knowledge-enhanced-automated-radiology","title":"KARGEN: Knowledge-enhanced Automated Radiology Report Generation Using Large Language Models","date":"2024-09-09","arxiv_id":"2409.05370","repositories_listed":0,"syntology":null},{"url":null,"slug":"action-is-the-primary-key-a-categorical","title":"Action is the primary key: a categorical framework for episode description and logical reasoning","date":"2024-09-07","arxiv_id":"2409.04793","repositories_listed":0,"syntology":null},{"url":null,"slug":"testing-and-evaluation-of-large-language","title":"Testing and Evaluation of Large Language Models: Correctness, Non-Toxicity, and Fairness","date":"2024-08-31","arxiv_id":"2409.00551","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-based-multi-hop-question-answering-with","title":"LLM-Based Multi-Hop Question Answering with Knowledge Graph Integration in Evolving Environments","date":"2024-08-28","arxiv_id":"2408.15903","repositories_listed":0,"syntology":null},{"url":null,"slug":"story3d-agent-exploring-3d-storytelling","title":"Story3D-Agent: Exploring 3D Storytelling Visualization with Large Language Models","date":"2024-08-21","arxiv_id":"2408.11801","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-evaluating-large-language-models-on","title":"SarcasmBench: Towards Evaluating Large Language Models on Sarcasm Understanding","date":"2024-08-21","arxiv_id":"2408.11319","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-mechanistic-interpretation-of-syllogistic","title":"A Mechanistic Interpretation of Syllogistic Reasoning in Auto-Regressive Language Models","date":"2024-08-16","arxiv_id":"2408.08590","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-might-not-care-what-you","title":"Large Language Models Might Not Care What You Are Saying: Prompt Format Beats Descriptions","date":"2024-08-16","arxiv_id":"2408.08780","repositories_listed":0,"syntology":null},{"url":null,"slug":"llmi3d-empowering-llm-with-3d-perception-from","title":"LLMI3D: Empowering LLM with 3D Perception from a Single 2D Image","date":"2024-08-14","arxiv_id":"2408.07422","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-large-language-models-reason-a","title":"Can Large Language Models Reason? A Characterization via 3-SAT","date":"2024-08-13","arxiv_id":"2408.07215","repositories_listed":0,"syntology":null},{"url":null,"slug":"p3-a-policy-driven-pace-adaptive-and","title":"P3: A Policy-Driven, Pace-Adaptive, and Diversity-Promoted Framework for data pruning in LLM Training","date":"2024-08-10","arxiv_id":"2408.05541","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-theorem-provers-help-improve-large","title":"Automated Theorem Provers Help Improve Large Language Model Reasoning","date":"2024-08-07","arxiv_id":"2408.03492","repositories_listed":0,"syntology":null},{"url":null,"slug":"lifelong-personalized-low-rank-adaptation-of","title":"Lifelong Personalized Low-Rank Adaptation of Large Language Models for Recommendation","date":"2024-08-07","arxiv_id":"2408.03533","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-large-language-models-with-chain","title":"Leveraging Large Language Models with Chain-of-Thought and Prompt Engineering for Traffic Crash Severity Analysis and Inference","date":"2024-08-04","arxiv_id":"2408.04652","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-00024","title":"Deceptive AI systems that give explanations are more convincing than honest AI systems and can amplify belief in misinformation","date":"2024-07-31","arxiv_id":"2408.00024","repositories_listed":0,"syntology":null},{"url":null,"slug":"clr-fact-evaluating-the-complex-logical","title":"CLR-Fact: Evaluating the Complex Logical Reasoning Capability of Large Language Models over Factual Knowledge","date":"2024-07-30","arxiv_id":"2407.20564","repositories_listed":0,"syntology":null},{"url":null,"slug":"take-a-step-back-rethinking-the-two-stages-in","title":"Take A Step Back: Rethinking the Two Stages in Visual Reasoning","date":"2024-07-29","arxiv_id":"2407.19666","repositories_listed":0,"syntology":null}],"record_sha256":"d4e8eeae33b02716aafc600457f5232329bd16a3b888d50facea7ade37df03e8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}