A comprehensive study on language models’ performance across 10 Indic languages.
― 7 min read
Computer Science - Computation and Language
RSSThis article presents a method for real-time spam review detection and explainability.
― 7 min read
A model that protects personal data in Italian legal writings.
― 8 min read
Research highlights in-context learning abilities in large language models.
― 6 min read
LLM2FEA combines generative AI and evolutionary algorithms for innovative design solutions.
― 10 min read
InternLM-Law enhances responses to diverse Chinese legal questions with advanced training.
― 7 min read
This study investigates public views on homelessness using social media analysis.
― 4 min read
A new method improves code repair for underused programming languages.
― 6 min read
A new system for accurate and fast speech translation across multiple languages.
― 6 min read
New techniques improve large language models' reasoning and logic performance.
― 6 min read
Exploring how user profiles improve personalization in language models.
― 6 min read
A study examines how well LLMs reason with graph data.
― 5 min read
A new model enhances event reference recognition across multiple documents.
― 6 min read
A new framework improves language models' representation of diverse human values.
― 7 min read
Research shows how multilingual feedback can enhance language model reliability.
― 5 min read
A study on Italy's regional languages using advanced speech analysis techniques.
― 9 min read
Research shows models struggle with step dependencies in cooking recipes.
― 5 min read
Exploring how attention sinks impact language model performance and introducing a calibration technique.
― 5 min read
Analyzing AI models' performance on children's math problems reveals significant gaps.
― 4 min read
RankAdaptor optimizes fine-tuning for pruned AI models, enhancing performance efficiently.
― 8 min read
INDICT enhances code safety and helpfulness using dual critique analysis.
― 6 min read
A study on PlagBench and its role in detecting plagiarism in LLM outputs.
― 4 min read
Research highlights how prompts affect AI-generated text detection accuracy.
― 4 min read
Research assesses language models' claim verification abilities using a new dataset.
― 5 min read
This article examines how certain neurons affect uncertainty in language model predictions.
― 6 min read
This paper presents a method to assess language models across various prompts.
― 6 min read
A new method improves machine dialogue through pseudo-stereo data.
― 6 min read
Learn about methods to measure translation quality effectively.
― 5 min read
This study presents a dataset and method to enhance Chinese ASR accuracy using Pinyin.
― 7 min read
A new dataset assesses LLM performance in solving graph-related challenges.
― 6 min read
New method addresses regional differences in gender bias evaluation.
― 6 min read
New methods refine reasoning skills in language models for better task performance.
― 7 min read
A new method for better understanding events by using multiple documents.
― 6 min read
MPCoder tailors code to individual developers’ styles, improving productivity and code quality.
― 7 min read
MIGU enhances continuous learning in language models without needing old data.
― 7 min read
A fresh approach to AI combines language models with symbolic programs for better interpretability.
― 8 min read
A study on the impact of images and text in gun violence news framing.
― 7 min read
New dataset assesses LLMs' ability for complex logical reasoning tasks.
― 6 min read
A look at how AI models interpret human choices and the need for improvement.
― 6 min read
Learn how inference-time algorithms enhance text generation performance.
― 4 min read