NLP 2025 Poster Presentation Practice.

Paper Reading: [2401.12143v2] Anisotropy is Inherent to Self-Attention in Transformers

Paper Reading:  [2024.tacl-1.44/] Beyond Boundaries: A Human-like Approach for Question Answering over Structured and Unstructured Information Sources

Paper Reading: I Could’ve Asked That: Reformulating Unanswerable Questions

Paper Reading: Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Models

Paper Reading: On Memorization of Large Language Models in Logical Reasoning

Paper Reading: CR-LT-KGQA: A Knowledge Graph Question Answering Dataset Requiring Commonsense Reasoning and Long-Tail Knowledge

Paper Reading: Argument Mining as a Text-to-Text Generation Task

Paper Reading: SELF-[IN]CORRECT: LLMs Struggle with Discriminating Self-Generated Responses

Paper Reading: Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Models

Paper Reading: Joint Multi-Facts Reasoning Network for Complex Temporal Question Answering Over Knowledge Graph

Paper Reading: Discursive Socratic Questioning: Evaluating the Faithfulness of Language Models’ Understanding of Discourse Relations

Paper Reading: LANGBRIDGE: Multilingual Reasoning Without Multilingual Supervision

Paper Reading: FanOutQA: A Multi-Hop, Multi-Document Question Answering Benchmark for Large Language Models

Paper Reading: Explore then Determine: A GNN-LLM Synergy Framework for Reasoning over Knowledge Graph

Paper Reading: What Evidence Do Language Models Find Convincing?

Paper Reading: Missci: Reconstructing Fallacies in Misrepresented Science

Paper Reading: Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning

Paper Reading: MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning

Paper Reading: A Dataset and Multi-task Multi-view Approach for Question-Answering with the Dual Perspectives of Text and Knowledge

Paper Reading: Survey on argumentation, and LLM evaluation. Related paper: • The Generative AI Paradox: “What It Can Create, It May Not Understand” • Evaluation of an LLM in Identifying Logical Fallacies • Large Language Models are Better Logical Fallacy Reasoners with Counterargument, Goal, and Explanation-aware Prompt Formulation • Distinguishing Logical Fallacies from Valid Arguments • Case-Based Reasoning with Language Models for Classification of Logical Fallacies

Paper Reading: NL2FOL: Translating Natural Language to First-Order Logic for Logical Fallacy Detection

Paper Reading: Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning

Paper Reading: Reason from Fallacy: Enhancing Large Language Models’ Logical Reasoning through Logical Fallacy Understanding

Paper Reading: When LLMs Meet Cunning Questions: A Fallacy Understanding Benchmark for Large Language Models

Paper Reading: Multi-hop question answering over incomplete knowledge graph with abstract conceptual evidence

Paper reading: Lin et al. Argue with Me Tersely: Towards Sentence-Level Counter-Argument Generation. EMNLP2023

Paper Reading: Do Large Language Models Latently Perform Multi-Hop Reasoning?

Paper Reading: Argument-based Detection and Classification of Fallacies in Political Debates

Paper Reading: StoryARG: a corpus of narratives and personal experiences in argumentative texts

Paper Reading: MAFALDA: A Benchmark and Comprehensive Study of Fallacy Detection and Classification

Irfan and Kim Poster

Paper Gathering

Paper Reading: Boundary Detection and Categorization of Argument Aspects via Supervised Learning

Paper Reading: Logical fallacies and Enhancing Cross-Domain Generalization through Data Augmentation with Reduced Uncertainty

Paper Reading: Detecting Narrative Elements in Informational Text

Paper Reading: Large Language Models are Few-Shot Training Example Generators: A Case Study in Fallacy Recognition

Paper Reading: A Robustness Evaluation Framework for Argument Mining

Paper Reading: Do Discourse Indicators Reflect the Main Arguments in Scientific Papers?

Paper Reading: Multi-Task Attentive Residual Networks for Argument Mining

PaperCan large language models provide useful feedback on research papers? A large-scale empirical analysis

Personal Long Report

Personal Long Report

Logistic Meeting

Paper Reading: SNaC: Coherence Error Detection for Narrative Summarization. EMNLP2022.

Paper Reading: Goffredo et al. Fallacious Argument Classification in Political Debates. IJCAI2022.

Paper Reading: Heng et al. Socratic Question Generation: A Novel Dataset, Models, and Evaluation. EACL2023.

Paper Reading: Argument Mining for Scholarly Document Processing: Taking Stock and Looking Ahead

Paper Reading: Classifying Argumentative Relations Using Logical Mechanisms and Argumentation Schemes

Paper Reading: Modeling Appropriate Language in Argumentation

Paper Reading: Case-Based Reasoning with Language Models for Classification of Logical Fallacies

Paper Reading: Can ChatGPT and Bard Generate Aligned Assessment Items? A Reliability Analysis against Human Performance

Research Presentation: Like Father, Like Son: Large Language Models Empower Smaller Language Models for Zero-shot Fallacy Detection

Research Presentation: Fallacious Detection using Generated Dataset from GPT3.5

Paper Reading: Survey on Automated Short Answer Grading with Deep Learning: from Word Embeddings to Transformers

Paper Reading: The Legal Argument Reasoning Task in Civil Procedure

Research Presentation: Fallacious Detection Research

Paper Reading: Humans in Humans Out: On GPT Converging Towards Common Sense in Both Success and Failure

Introduction