ArXiv NLP research for Thursday, June 06, 2024.
00:20: The syntax-semantics interface in a child's path: A study of 3- to 11-year-olds' elicited production of Mandarin recursive relative clauses
02:17: Ask LLMs Directly, "What shapes your bias?": Measuring Social Bias in Large Language Models
03:39: Explainability and Hate Speech: Structured Explanations Make Social Media Moderators Faster
04:36: Intention and Face in Dialog
05:48: Uncovering Limitations of Large Language Models in Information Seeking from Tables
07:15: Are We Done with MMLU?
08:41: Legal Judgment Reimagined: PredEx and the Rise of Intelligent AI Interpretation in Indian Courts
09:53: Do Language Models Understand Morality? Towards a Robust Detection of Moral Content
11:47: Every Answer Matters: Evaluating Commonsense with Probabilistic Measures
12:49: Towards Understanding Task-agnostic Debiasing Through the Lenses of Intrinsic Bias and Forgetfulness
14:26: Pointer-Guided Pre-Training: Infusing Large Language Models with Paragraph-Level Contextual Awareness
15:35: Confabulation: The Surprising Value of Large Language Model Hallucinations
16:42: DICE: Detecting In-distribution Contamination in LLM's Fine-tuning Phase for Math Reasoning
18:25: Legal Documents Drafting with Fine-Tuned Pre-Trained Large Language Model
19:32: ValueBench: Towards Comprehensively Evaluating Value Orientations and Understanding of Large Language Models
20:50: mCSQA: Multilingual Commonsense Reasoning Dataset with Unified Creation Strategy by Language Models and Humans
22:21: What Do Language Models Learn in Context? The Structured Task Hypothesis
23:38: Rethinking LLM and Linguistic Steganalysis: An Efficient Detection of Strongly Concealed Stego
24:58: BEADs: Bias Evaluation Across Domains
26:41: FairytaleQA Translated: Enabling Educational Question and Answer Generation in Less-Resourced Languages
28:03: Benchmark Data Contamination of Large Language Models: A Survey
29:02: Transformers need glasses! Information over-squashing in language tasks
30:26: Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models
31:58: Characterizing Similarities and Divergences in Conversational Tones in Humans and LLMs by Sampling with People
33:44: ABEX: Data Augmentation for Low-Resource NLU via Expanding Abstract Descriptions
35:19: What Languages are Easy to Language-Model? A Perspective from Learning Probabilistic Regular Languages
36:41: PaCE: Parsimonious Concept Engineering for Large Language Models