Recently Read

#

Papers/articles I’ve read and want to keep track of for future reference. Papers listed in my awesome_slop repo are not duplicated here

#

• Do you actually need an LLM? Rethinking language models for customer reviews analysis
• SONAR: Sentence-Level Multimodal and Language-Agnostic Representations
• Unveiling the intensity–ambiguity relationships among affective and lexico‑semantic variables in Chinese characters and the character–word relationships in Chinese two‑character words
• A survey on cutting-edge relation extraction techniques based on language models
• Titans: Learning to Memorize at Test Time
• Diffusion models in text generation: a survey
• Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-Based Retrofitting
• Large Language Diffusion Models
• A Graph-to-Sequence Model for AMR-to-Text Generation
• Neural Text Generation in Stories Using Entity Representations as Context
• Neural Text Generation with Unlikelihood Training
• Kernelized Bayesian Softmax for Text Generation
• Text Generation from Knowledge Graphs with Graph Transformers
• Using NLU in Context for Question Answering: Improving on Facebook’s bAbI Tasks
• A Summary of Role and Reference Grammar
• Energy-Based Transformers are Scalable Learners and Thinkers
• node2vec: Scalable Feature Learning for Networks
• Benchmarking machine learning methods for the identification of mislabeled data
• Efficient deep neural unification in symbolic processing
• UniBERT: adversarial training for language-universal representations
• A review of state-of-the-art techniques for large language model compression
• Reward as a facet of word meaning: Ratings of motivation for 8,601 English words
• How adults’ experience with words changes over time: Insights from five years of the Wesleyan Word Experience Project
• Toward practical human-interpretable explanations
• Assessing the risk of discriminatory bias in classification datasets
• SoftMatcha: A Soft and Fast Pattern Matcher for Billion-Scale Corpus Searches
• The Polish vocabulary size test: A novel adaptive test for receptive vocabulary assessment
• Rethinking Graph Transformers with Spectral Attention
• Scaling Up Graph Neural Networks Via Graph Coarsening
• Graph Transformer Networks
• Switchboard-Affect: Emotion Perception Labels from Conversational Speech
• FS-DFM: Fast and Accurate Long Text Generation with Few-Step Diffusion Language Models
• mRAKL: Multilingual Retrieval-Augmented Knowledge Graph Construction for Low-Resourced Languages
• A phase transition between positional and semantic learning in a solvable model of dot-product attention
• Few-shot Named Entity Recognition via encoder and class intervention
• Label-aware debiased causal reasoning for Natural Language Inference
• Optimal RoPE extension via Bayesian Optimization for training-free length generalization
• Measuring Research Difficulty in Academic Papers: A Case Study in Natural Language Processing
• Text clustering with large language model embeddings
• A novel region based neighbors searching classification algorithm for big data
• Continuous Thought Machines
• Text Embeddings Reveal (Almost) As Much As Text
• Spherical Text Embedding
• LLM Internal States Reveal Hallucination Risk Faced With a Query
• TQC: An intelligent clustering approach for large-scale, noisy, and imbalanced data
• What Are “Good” Rhythms? Generating Rhythms Based on the Properties Set Out in The Geometry of Musical Rhythm
• From Data to Insight: Topic Modelling and Automatic Topic Labelling Strategies
• Hierarchical Geometry of Cognitive States in Transformer Embedding Spaces
• Modeling Language as a Sequence of Thoughts
• Incoherence as Oracle-less Measure of Error in LLM-Based Code Generation
• Thought Anchors: Which LLM Reasoning Steps Matter?
• Catastrophic Failure of LLM Unlearning via Quantization
• Estimating the reproducibility of psychological science