• NLI
• Paraphrase
• Summarization
• Semantic Parsing
• Question Answering
• Sentiment Analysis
• Dialogue Agents

• Types of Neurosymbolic Methods
• Knowledge representation
• Knowledge graphs
• Reasoning using Neurosymbolic methods

• Chain-of-thought
• Language policy
• Reward Modeling
• Policy Optimization

• Adversarial Objectives
• Datasets for providing feedback
• Self-Reflection
• Critics
• Judges

• Cooperative Inverse RL
• Preference Learning
• Constitutional Optimization

• Adversarial Truthfulness Regulation
• Truthfulness as an Environmental Constraint
• Self-Reflective Belief Tracking

• Intent Classification: Predicting semantic continuity based on topic modeling & named entity chains.

• PPO
• DPO
• Alignment with Human Preferences

• Types of reasoning
• Recent methods of evaluating reasoning

• NeSy summary and example implementations

Note: Please email me to request access to the respective private submodules/repositories.

@online{sakoju-github-works-study-list,
	title        = {github sakoju/recent-works},
	author       = {sushmaanandakoju},
	year         = {2023-2025},
	note         = {[Accessed in 2025]},
	howpublished = {\url{https://github.com/sushmaakoju/recent-works}}
}