{"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/reading-comprehension/papers/8","list_of":"/task/reading-comprehension","task":"Reading Comprehension","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":8,"pages_in_order":18,"rows_per_page":100,"rows":[701,800],"of":1760,"counts":{"archive_papers_tagged":1760,"with_a_code_link":634,"where_syntology_ran_a_sample":139,"not_listed_spam_title":0,"listed":1760,"listed_where_code_ran":139,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":120,"every_run_a_failure_of_syntologys_instrument":19,"listed_with_a_run_with_no_instrument_failure":120,"listed_every_run_a_failure_of_syntologys_instrument":19,"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/reading-comprehension","prev":"/task/reading-comprehension/papers/7","next":"/task/reading-comprehension/papers/9","papers":[{"url":null,"slug":"clinical-reading-comprehension-with-encoder","title":"Clinical Reading Comprehension with Encoder-Decoder Models Enhanced by Direct Preference Optimization","date":"2024-07-19","arxiv_id":"2407.14000","repositories_listed":0,"syntology":null},{"url":null,"slug":"struct-x-enhancing-large-language-models","title":"Struct-X: Enhancing Large Language Models Reasoning with Structured Data","date":"2024-07-17","arxiv_id":"2407.12522","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-as-misleading","title":"Large Language Models as Misleading Assistants in Conversation","date":"2024-07-16","arxiv_id":"2407.11789","repositories_listed":0,"syntology":null},{"url":null,"slug":"look-within-why-llms-hallucinate-a-causal","title":"Look Within, Why LLMs Hallucinate: A Causal Perspective","date":"2024-07-14","arxiv_id":"2407.10153","repositories_listed":0,"syntology":null},{"url":null,"slug":"sphinx-sample-efficient-multilingual","title":"sPhinX: Sample Efficient Multilingual Instruction Fine-Tuning Through N-shot Guided Prompting","date":"2024-07-13","arxiv_id":"2407.09879","repositories_listed":0,"syntology":null},{"url":null,"slug":"have-we-reached-agi-comparing-chatgpt-claude","title":"Have We Reached AGI? Comparing ChatGPT, Claude, and Gemini to Human Literacy and Education Benchmarks","date":"2024-07-11","arxiv_id":"2407.09573","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":"/paper/rvisa-reasoning-and-verification-for-implicit","slug":"rvisa-reasoning-and-verification-for-implicit","title":"RVISA: Reasoning and Verification for Implicit Sentiment Analysis","date":"2024-07-02","arxiv_id":"2407.02340","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-of-instruction-following-ability","title":"Evaluation of Instruction-Following Ability for Large Language Models on Story-Ending Generation","date":"2024-06-24","arxiv_id":"2406.16356","repositories_listed":0,"syntology":null},{"url":null,"slug":"it-is-not-about-what-you-say-it-is-about-how","title":"It Is Not About What You Say, It Is About How You Say It: A Surprisingly Simple Approach for Improving Reading Comprehension","date":"2024-06-24","arxiv_id":"2406.16779","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-open-source-language-models-for","title":"Comparison of Open-Source and Proprietary LLMs for Machine Reading Comprehension: A Practical Analysis for Industrial Applications","date":"2024-06-19","arxiv_id":"2406.13713","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-robustness-of-language-models-for","title":"Exploring the Robustness of Language Models for Tabular Question Answering via Attention Analysis","date":"2024-06-18","arxiv_id":"2406.12719","repositories_listed":0,"syntology":null},{"url":null,"slug":"internalinspector-i-2-robust-confidence","title":"InternalInspector $I^2$: Robust Confidence Estimation in LLMs through Internal States","date":"2024-06-17","arxiv_id":"2406.12053","repositories_listed":0,"syntology":null},{"url":null,"slug":"vega-learning-interleaved-image-text","title":"VEGA: Learning Interleaved Image-Text Comprehension in Vision-Language Large Models","date":"2024-06-14","arxiv_id":"2406.10228","repositories_listed":0,"syntology":null},{"url":null,"slug":"2dp-2mrc-2-dimensional-pointer-based-machine","title":"2DP-2MRC: 2-Dimensional Pointer-based Machine Reading Comprehension Method for Multimodal Moment Retrieval","date":"2024-06-10","arxiv_id":"2406.06201","repositories_listed":0,"syntology":null},{"url":null,"slug":"coherent-zero-shot-visual-instruction","title":"Coherent Zero-Shot Visual Instruction Generation","date":"2024-06-06","arxiv_id":"2406.04337","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-distractor-generation-via-large","title":"Unsupervised Distractor Generation via Large Language Model Distilling and Counterfactual Contrastive Decoding","date":"2024-06-03","arxiv_id":"2406.01306","repositories_listed":0,"syntology":null},{"url":null,"slug":"brainstorming-brings-power-to-large-language","title":"Brainstorming Brings Power to Large Language Models of Knowledge Reasoning","date":"2024-06-02","arxiv_id":"2406.06561","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-clarify-multi-turn-conversations","title":"Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training","date":"2024-05-31","arxiv_id":"2406.00222","repositories_listed":0,"syntology":null},{"url":null,"slug":"long-span-question-answering-automatic","title":"Long-Span Question-Answering: Automatic Question Generation and QA-System Ranking via Side-by-Side Evaluation","date":"2024-05-31","arxiv_id":"2406.00179","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-gpt-redefine-medical-understanding","title":"Can GPT Redefine Medical Understanding? Evaluating GPT on Biomedical Machine Reading Comprehension","date":"2024-05-29","arxiv_id":"2405.18682","repositories_listed":0,"syntology":null},{"url":null,"slug":"dgrc-an-effective-fine-tuning-framework-for","title":"DGRC: An Effective Fine-tuning Framework for Distractor Generation in Chinese Multi-choice Reading Comprehension","date":"2024-05-29","arxiv_id":"2405.19139","repositories_listed":0,"syntology":null},{"url":null,"slug":"time-matters-enhancing-pre-trained-news","title":"Time Matters: Enhancing Pre-trained News Recommendation Models with Robust User Dwell Time Injection","date":"2024-05-21","arxiv_id":"2405.12486","repositories_listed":0,"syntology":null},{"url":null,"slug":"auto-faq-generation","title":"Auto FAQ Generation","date":"2024-05-13","arxiv_id":"2405.13006","repositories_listed":0,"syntology":null},{"url":null,"slug":"compressing-long-context-for-enhancing-rag","title":"Compressing Long Context for Enhancing RAG with AMR-based Concept Distillation","date":"2024-05-06","arxiv_id":"2405.03085","repositories_listed":0,"syntology":null},{"url":null,"slug":"mmger-multi-modal-and-multi-granularity","title":"MMGER: Multi-modal and Multi-granularity Generative Error Correction with LLM for Joint Accent and Speech Recognition","date":"2024-05-06","arxiv_id":"2405.03152","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-large-language-models-make-the-grade-an","title":"Can Large Language Models Make the Grade? An Empirical Study Evaluating LLMs Ability to Mark Short Answer Questions in K-12 Education","date":"2024-05-05","arxiv_id":"2405.02985","repositories_listed":0,"syntology":null},{"url":null,"slug":"qlsc-a-query-latent-semantic-calibrator-for","title":"QLSC: A Query Latent Semantic Calibrator for Robust Extractive Question Answering","date":"2024-04-30","arxiv_id":"2404.19316","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-llm-inference-with-kcache","title":"Efficient LLM Inference with Kcache","date":"2024-04-28","arxiv_id":"2404.18057","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-pre-trained-generative-language","title":"Enhancing Pre-Trained Generative Language Models with Question Attended Span Extraction on Machine Reading Comprehension","date":"2024-04-27","arxiv_id":"2404.17991","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-learning-enhanced-single-choice","title":"Transfer Learning Enhanced Single-choice Decision for Multi-choice Question Answering","date":"2024-04-27","arxiv_id":"2404.17949","repositories_listed":0,"syntology":null},{"url":null,"slug":"pdf-mvqa-a-dataset-for-multimodal-information","title":"PDF-MVQA: A Dataset for Multimodal Information Retrieval in PDF-based Visual Question Answering","date":"2024-04-19","arxiv_id":"2404.12720","repositories_listed":0,"syntology":null},{"url":null,"slug":"emrqa-msquad-a-medical-dataset-structured","title":"emrQA-msquad: A Medical Dataset Structured with the SQuAD V2.0 Framework, Enriched with emrQA Medical Information","date":"2024-04-18","arxiv_id":"2404.12050","repositories_listed":0,"syntology":null},{"url":null,"slug":"fewer-truncations-improve-language-modeling","title":"Fewer Truncations Improve Language Modeling","date":"2024-04-16","arxiv_id":"2404.10830","repositories_listed":0,"syntology":null},{"url":null,"slug":"question-difficulty-ranking-for-multiple","title":"Question Difficulty Ranking for Multiple-Choice Reading Comprehension","date":"2024-04-16","arxiv_id":"2404.10704","repositories_listed":0,"syntology":null},{"url":null,"slug":"causalbench-a-comprehensive-benchmark-for","title":"CausalBench: A Comprehensive Benchmark for Causal Learning Capability of LLMs","date":"2024-04-09","arxiv_id":"2404.06349","repositories_listed":0,"syntology":null},{"url":null,"slug":"llms-reading-comprehension-is-affected-by","title":"LLMs' Reading Comprehension Is Affected by Parametric Knowledge and Struggles with Hypothetical Statements","date":"2024-04-09","arxiv_id":"2404.06283","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-hallucinations-leaderboard-an-open-effort","title":"The Hallucinations Leaderboard -- An Open Effort to Measure Hallucinations in Large Language Models","date":"2024-04-08","arxiv_id":"2404.05904","repositories_listed":0,"syntology":null},{"url":null,"slug":"xl-2-bench-a-benchmark-for-extremely-long","title":"XL$^2$Bench: A Benchmark for Extremely Long Context Understanding with Long-range Dependencies","date":"2024-04-08","arxiv_id":"2404.05446","repositories_listed":0,"syntology":null},{"url":null,"slug":"explaining-eda-synthesis-errors-with-llms","title":"LLM-aided explanations of EDA synthesis errors","date":"2024-04-07","arxiv_id":"2404.07235","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-autonomous-agents-through-the-lens","title":"Exploring Autonomous Agents through the Lens of Large Language Models: A Review","date":"2024-04-05","arxiv_id":"2404.04442","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-death-of-feature-engineering-bert-with","title":"The Death of Feature Engineering? BERT with Linguistic Features on SQuAD 2.0","date":"2024-04-04","arxiv_id":"2404.03184","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-nexus-of-large-language-models","title":"Exploring the Nexus of Large Language Models and Legal Systems: A Short Survey","date":"2024-04-01","arxiv_id":"2404.00990","repositories_listed":0,"syntology":null},{"url":null,"slug":"gpt-4-understands-discourse-at-least-as-well","title":"Text Understanding in GPT-4 vs Humans","date":"2024-03-25","arxiv_id":"2403.17196","repositories_listed":0,"syntology":null},{"url":null,"slug":"mrc-based-nested-medical-ner-with-co","title":"MRC-based Nested Medical NER with Co-prediction and Adaptive Pre-training","date":"2024-03-23","arxiv_id":"2403.15800","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-human-like-machine-comprehension-few","title":"Towards Human-Like Machine Comprehension: Few-Shot Relational Learning in Visually-Rich Documents","date":"2024-03-23","arxiv_id":"2403.15765","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-condensation-and-reasoning-for","title":"Knowledge Condensation and Reasoning for Knowledge-based VQA","date":"2024-03-15","arxiv_id":"2403.10037","repositories_listed":0,"syntology":null},{"url":null,"slug":"cuentosie-can-a-chatbot-about-tales-with-a","title":"CuentosIE: can a chatbot about \"tales with a message\" help to teach emotional intelligence?","date":"2024-03-11","arxiv_id":"2403.07193","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-psychology-of-machines-large","title":"Towards a Psychology of Machines: Large Language Models Predict Human Memory","date":"2024-03-08","arxiv_id":"2403.05152","repositories_listed":0,"syntology":null},{"url":null,"slug":"saullm-7b-a-pioneering-large-language-model","title":"SaulLM-7B: A pioneering Large Language Model for Law","date":"2024-03-06","arxiv_id":"2403.03883","repositories_listed":0,"syntology":null},{"url":null,"slug":"acemap-knowledge-discovery-through-academic","title":"AceMap: Knowledge Discovery through Academic Graph","date":"2024-03-05","arxiv_id":"2403.02576","repositories_listed":0,"syntology":null},{"url":null,"slug":"choose-your-own-adventure-interactive-e-books","title":"Choose Your Own Adventure: Interactive E-Books to Improve Word Knowledge and Comprehension Skills","date":"2024-03-04","arxiv_id":"2403.02496","repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-learning-performance-with-large","title":"Predicting Learning Performance with Large Language Models: A Study in Adult Literacy","date":"2024-03-04","arxiv_id":"2403.14668","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-large-language-models-mirror-cognitive","title":"Do Large Language Models Mirror Cognitive Language Processing?","date":"2024-02-28","arxiv_id":"2402.18023","repositories_listed":0,"syntology":null},{"url":null,"slug":"qase-enhanced-plms-improved-control-in-text","title":"QASE Enhanced PLMs: Improved Control in Text Generation for MRC","date":"2024-02-26","arxiv_id":"2403.04771","repositories_listed":0,"syntology":null},{"url":null,"slug":"cliqueparcel-an-approach-for-batching-llm","title":"CliqueParcel: An Approach For Batching LLM Prompts That Jointly Optimizes Efficiency And Faithfulness","date":"2024-02-17","arxiv_id":"2402.14833","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-human-inspired-reading-agent-with-gist","title":"A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts","date":"2024-02-15","arxiv_id":"2402.09727","repositories_listed":0,"syntology":null},{"url":null,"slug":"minds-versus-machines-rethinking-entailment","title":"Are Machines Better at Complex Reasoning? Unveiling Human-Machine Inference Gaps in Entailment Verification","date":"2024-02-06","arxiv_id":"2402.03686","repositories_listed":0,"syntology":null},{"url":"/paper/multi-multimodal-understanding-leaderboard","slug":"multi-multimodal-understanding-leaderboard","title":"MULTI: Multimodal Understanding Leaderboard with Text and Images","date":"2024-02-05","arxiv_id":"2402.03173","repositories_listed":0,"syntology":null},{"url":null,"slug":"socialite-llama-an-instruction-tuned-model","title":"SOCIALITE-LLAMA: An Instruction-Tuned Model for Social Scientific Tasks","date":"2024-02-03","arxiv_id":"2402.01980","repositories_listed":0,"syntology":null},{"url":null,"slug":"paramanu-a-family-of-novel-efficient-indic","title":"Paramanu: A Family of Novel Efficient Generative Foundation Language Models for Indian Languages","date":"2024-01-31","arxiv_id":"2401.18034","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-gender-bias-in-large-language","title":"Evaluating Gender Bias in Large Language Models via Chain-of-Thought Prompting","date":"2024-01-28","arxiv_id":"2401.15585","repositories_listed":0,"syntology":null},{"url":null,"slug":"persona-centric-metamorphic-relation-guided","title":"Persona-centric Metamorphic Relation guided Robustness Evaluation for Multi-turn Dialogue Modelling","date":"2024-01-23","arxiv_id":"2401.12483","repositories_listed":0,"syntology":null},{"url":null,"slug":"majority-or-minority-data-imbalance-learning","title":"Majority or Minority: Data Imbalance Learning Method for Named Entity Recognition","date":"2024-01-21","arxiv_id":"2401.11431","repositories_listed":0,"syntology":null},{"url":null,"slug":"power-in-numbers-robust-reading-comprehension","title":"Power in Numbers: Robust reading comprehension by finetuning with four adversarial sentences per example","date":"2024-01-18","arxiv_id":"2401.10091","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-perplexity-for-controlled","title":"Contrastive Perplexity for Controlled Generation: An Application in Detoxifying Large Language Models","date":"2024-01-16","arxiv_id":"2401.08491","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-are-null-shot-learners","title":"Large Language Models are Null-Shot Learners","date":"2024-01-16","arxiv_id":"2401.08273","repositories_listed":0,"syntology":null},{"url":null,"slug":"developing-chatgpt-for-biology-and-medicine-a","title":"Developing ChatGPT for Biology and Medicine: A Complete Review of Biomedical Question Answering","date":"2024-01-15","arxiv_id":"2401.07510","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-what-why-and-how-of-context-length","title":"The What, Why, and How of Context Length Extension Techniques in Large Language Models -- A Detailed Survey","date":"2024-01-15","arxiv_id":"2401.07872","repositories_listed":0,"syntology":null},{"url":null,"slug":"structsum-generation-for-faster-text","title":"Structsum Generation for Faster Text Comprehension","date":"2024-01-12","arxiv_id":"2401.06837","repositories_listed":0,"syntology":null},{"url":null,"slug":"attendre-wait-to-attend-by-retrieval-with","title":"Attendre: Wait To Attend By Retrieval With Evicted Queries in Memory-Based Transformers for Long Context Processing","date":"2024-01-10","arxiv_id":"2401.04881","repositories_listed":0,"syntology":null},{"url":null,"slug":"cosmo-contrastive-streamlined-multimodal","title":"COSMO: COntrastive Streamlined MultimOdal Model with Interleaved Pre-Training","date":"2024-01-01","arxiv_id":"2401.00849","repositories_listed":0,"syntology":null},{"url":null,"slug":"probing-pretrained-language-models-with","title":"Probing Pretrained Language Models with Hierarchy Properties","date":"2023-12-15","arxiv_id":"2312.09670","repositories_listed":0,"syntology":null},{"url":null,"slug":"high-throughput-biomedical-relation","title":"High-throughput Biomedical Relation Extraction for Semi-Structured Web Articles Empowered by Large Language Models","date":"2023-12-13","arxiv_id":"2312.08274","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-large-language-models-are-all","title":"Generative Large Language Models Are All-purpose Text Analytics Engines: Text-to-text Learning Is All Your Need","date":"2023-12-11","arxiv_id":"2312.06099","repositories_listed":0,"syntology":null},{"url":null,"slug":"think-from-words-tfw-initiating-human-like","title":"Think from Words(TFW): Initiating Human-Like Cognition in Large Language Models Through Think from Words for Japanese Text-level Classification","date":"2023-12-06","arxiv_id":"2312.03458","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-the-rationale-understanding-of","title":"Evaluating the Rationale Understanding of Critical Reasoning in Logical Reading Comprehension","date":"2023-11-30","arxiv_id":"2311.18353","repositories_listed":0,"syntology":null},{"url":"/paper/orca-2-teaching-small-language-models-how-to","slug":"orca-2-teaching-small-language-models-how-to","title":"Orca 2: Teaching Small Language Models How to Reason","date":"2023-11-18","arxiv_id":"2311.11045","repositories_listed":0,"syntology":null},{"url":null,"slug":"complementary-advantages-of-chatgpts-and","title":"Complementary Advantages of ChatGPTs and Human Readers in Reasoning: Evidence from English Text Reading Comprehension","date":"2023-11-17","arxiv_id":"2311.10344","repositories_listed":0,"syntology":null},{"url":null,"slug":"measuring-and-improving-attentiveness-to","title":"Measuring and Improving Attentiveness to Partial Inputs with Counterfactuals","date":"2023-11-16","arxiv_id":"2311.09605","repositories_listed":0,"syntology":null},{"url":null,"slug":"thread-of-thought-unraveling-chaotic-contexts","title":"Thread of Thought Unraveling Chaotic Contexts","date":"2023-11-15","arxiv_id":"2311.08734","repositories_listed":0,"syntology":null},{"url":null,"slug":"sharing-teaching-and-aligning-knowledgeable","title":"Sharing, Teaching and Aligning: Knowledgeable Transfer Learning for Cross-Lingual Machine Reading Comprehension","date":"2023-11-12","arxiv_id":"2311.06758","repositories_listed":0,"syntology":null},{"url":null,"slug":"bizbench-a-quantitative-reasoning-benchmark","title":"BizBench: A Quantitative Reasoning Benchmark for Business and Finance","date":"2023-11-11","arxiv_id":"2311.06602","repositories_listed":0,"syntology":null},{"url":null,"slug":"assessing-distractors-in-multiple-choice","title":"Assessing Distractors in Multiple-Choice Tests","date":"2023-11-08","arxiv_id":"2311.04554","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-recommendation-capabilities-of-gpt","title":"Exploring Recommendation Capabilities of GPT-4V(ision): A Preliminary Case Study","date":"2023-11-07","arxiv_id":"2311.04199","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-grained-evidence-inference-for-multi","title":"Multi-grained Evidence Inference for Multi-choice Reading Comprehension","date":"2023-10-27","arxiv_id":"2310.18070","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-llms-grade-short-answer-reading","title":"Can LLMs Grade Short-Answer Reading Comprehension Questions : An Empirical Study with a Novel Dataset","date":"2023-10-26","arxiv_id":"2310.18373","repositories_listed":0,"syntology":null},{"url":null,"slug":"explicit-alignment-and-many-to-many","title":"Explicit Alignment and Many-to-many Entailment Based Reasoning for Conversational Machine Reading","date":"2023-10-20","arxiv_id":"2310.13409","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-large-language-models-llms-to","title":"TF-DCon: Leveraging Large Language Models (LLMs) to Empower Training-Free Dataset Condensation for Content-Based Recommendation","date":"2023-10-15","arxiv_id":"2310.09874","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-consensus-game-language-model-generation","title":"The Consensus Game: Language Model Generation via Equilibrium Search","date":"2023-10-13","arxiv_id":"2310.09139","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-odia-braille-literacy-the","title":"Optimizing Odia Braille Literacy: The Influence of Speed on Error Reduction and Enhanced Comprehension","date":"2023-10-12","arxiv_id":"2310.08280","repositories_listed":0,"syntology":null},{"url":null,"slug":"lc-score-reference-less-estimation-of-text","title":"LC-Score: Reference-less estimation of Text Comprehension Difficulty","date":"2023-10-04","arxiv_id":"2310.02754","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-evaluation-framework-best","title":"Hierarchical Evaluation Framework: Best Practices for Human Evaluation","date":"2023-10-03","arxiv_id":"2310.01917","repositories_listed":0,"syntology":null},{"url":null,"slug":"gaze-driven-sentence-simplification-for","title":"Gaze-Driven Sentence Simplification for Language Learners: Enhancing Comprehension and Readability","date":"2023-09-30","arxiv_id":"2310.00355","repositories_listed":0,"syntology":null},{"url":null,"slug":"in-context-learning-in-large-language-models-1","title":"Decoding In-Context Learning: Neuroscience-inspired Analysis of Representations in Large Language Models","date":"2023-09-30","arxiv_id":"2310.00313","repositories_listed":0,"syntology":null},{"url":null,"slug":"chatgpt-bci-word-level-neural-state","title":"Integrating LLM, EEG, and Eye-Tracking Biomarker Analysis for Word-Level Neural State Classification in Semantic Inference Reading Comprehension","date":"2023-09-27","arxiv_id":"2309.15714","repositories_listed":0,"syntology":null},{"url":null,"slug":"question-answering-using-deep-learning-in-low","title":"Question answering using deep learning in low resource Indian language Marathi","date":"2023-09-27","arxiv_id":"2309.15779","repositories_listed":0,"syntology":null},{"url":null,"slug":"chatprcs-a-personalized-support-system-for","title":"ChatPRCS: A Personalized Support System for English Reading Comprehension based on ChatGPT","date":"2023-09-22","arxiv_id":"2309.12808","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-it-possible-to-modify-text-to-a-target","title":"Is it Possible to Modify Text to a Target Readability Level? An Initial Investigation Using Zero-Shot Large Language Models","date":"2023-09-22","arxiv_id":"2309.12551","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-llms-augment-low-resource-reading","title":"Can LLMs Augment Low-Resource Reading Comprehension Datasets? Opportunities and Challenges","date":"2023-09-21","arxiv_id":"2309.12426","repositories_listed":0,"syntology":null}],"record_sha256":"d1ecfdf1192a11fc02ab234976d845ccd9511c8e012b2dbdb0b8f73d6b782921","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}