| Dissecting Recall of Factual Associations in Auto-Regressive Language Models |  | 
 | :heavy_minus_sign: |
| Interpreting Embedding Spaces by Conceptualization |  |
 | :heavy_minus_sign: |
| Norm of Word Embedding Encodes Information Gain | :heavy_minus_sign: |
 | :heavy_minus_sign: |
| Assessing Step-by-Step Reasoning against Lexical Negation: A Case Study on Syllogism |  |
 | :heavy_minus_sign: |
| Can LLMs Facilitate Interpretation of Pre-Trained Language Models? |  |
 | :heavy_minus_sign: |
| Can You Follow Me? Testing Situational Understanding for ChatGPT |  |
 | :heavy_minus_sign: |
| Absolute Position Embedding Learns Sinusoid-Like Waves for Attention based on Relative Position | :heavy_minus_sign: | | :heavy_minus_sign: |
| Statistical Depth for Ranking and Characterizing Transformer-based Text Embeddings |  |
 | :heavy_minus_sign: |
| Explaining Interactions between Text Spans |  |
 | :heavy_minus_sign: |
| Bridging Information-Theoretic and Geometric Compression in Language Models | :heavy_minus_sign: |
 | :heavy_minus_sign: |
| What Comes Next? Evaluating Uncertainty in Neural Text Generators Against Human Production Variability |  |
 | :heavy_minus_sign: |
| Data Factors for Better Compositional Generalization |  |
 | :heavy_minus_sign: |
