CSCE 689 - Advanced Natural Language Processing

CSCE 689 - Advanced Natural Language Processing (Fall 2026)

Course Information

Lectures

Time: Monday/Wednesday 4:10pm – 5:25pm
Location: HRBB 126

Instructor

Kuan-Hao Huang
Email: khhuang [at] tamu [dot] edu
Office: PETR 219
Office Hour: Wednesday 2pm – 3pm

Readings (Optional)

Speech and Language Processing (3rd ed. draft), Dan Jurafsky and James H. Martin.

Grading

Grade

LaTeX Assignment (1%) [Due: 9/10]
Paper Summary (10%)
Feedback Form (10%)
Topic Study (30%)

Literature Review (15%) [Due: 10/1]
Topic Presentation (15%)

Course Project (49%)

Project Proposal (5%) [Due: 10/8]
Project Highlight Presentation (5%) [Due: 10/21]
Midterm Report (10%) [Due: 11/5]
Final Presentation (12%) [11/30, 12/2]
Final Report (17%) [Due: 12/6]

Late Policy

Literature Review, Project Proposal, Midterm Report, Final Report

1 day late: 10% penalty
2 days late: 20% penalty
3 days late: 30% penalty
4 days late: 50% penalty
5 or more days late: 100% penalty

LaTeX Assignment, Topic Presentation Slides, Feedback Form, and Others

No late submissions allowed

Schedule

Week	Date	Topic	Readings	Presenter
W1	8/24	Course Overview		Instructor
	8/26	NLP Basics	Machine Learning Basics, Word Representations	Instructor
W2	8/31	NLP Basics	Language Modeling, Convolutional Neural Network	Instructor
	9/2	NLP Basics	Recurrent Neural Network, Attention	Instructor
W3	9/7	Labor Day (No Class)
	9/9	NLP Basics	Transformers, Pre-Training	Instructor
	9/10	LaTeX Assignment Due
W4	9/14	NLP Basics	Large Language Models, Text Similarity	Instructor
	9/16	NLP Basics	Retrieval-Augmented Generation, Vision-Language Models	Instructor
W5	9/21	Alignment, Post-Training	Training language models to follow instructions with human feedback, NeurIPS 2022 Direct Preference Optimization: Your Language Model is Secretly a Reward Model, NeurIPS 2023 SimPO: Simple Preference Optimization with a Reference-Free Reward, NeurIPS 2024	Instructor
	9/23	Test-Time Scaling, Reasoning Models	s1: Simple test-time scaling, EMNLP 2025 DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning, arXiv 2025 Understanding R1-Zero-Like Training: A Critical Perspective, COLM 2025	Instructor
W6	9/28	Model Efficiency	LoRA: Low-Rank Adaptation of Large Language Models, ICLR 2022 Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity, JMLR 2022 QLoRA: Efficient Finetuning of Quantized LLMs, NeurIPS 2023 CaM: Cache Merging for Memory-efficient LLMs Inference, ICML 2024
	9/30	Bias Detection and Mitigation	Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings, NeurIPS 2016 Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints, EMNLP 2017 BLIND: Bias Removal With No Demographics, ACL 2023 On Second Thought, Let’s Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning, ACL 2023
	10/1	Literature Review Due
W7	10/5	Invited Talk (Remote)
	10/7	Kuan-Hao is traveling (No Class)
	10/8	Project Proposal Due
W8	10/12	Project Highlight Presentation (Remote)
	10/14	Adversarial Attacks and Jailbreaking	Universal Adversarial Triggers for Attacking and Analyzing NLP, EMNLP 2019 BERT-ATTACK: Adversarial Attack Against BERT Using BERT, EMNLP 2020 Towards Robustness Against Natural Language Word Substitutions, ICLR 2021 Universal and Transferable Adversarial Attacks on Aligned Language Models, arXiv 2023 [Present]
W9	10/19	AI-Generated Text Detection	Defending Against Neural Fake News, NeurIPS 2019 DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature, ICML 2023 Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature, ICLR 2024 A Watermark for Large Language Models, ICML 2023 [Present]
	10/21	Hallucinations	SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models, EMNLP 2023 How Language Model Hallucinations Can Snowball, ICML 2024 Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps, EMNLP 2024 Chain-of-Verification Reduces Hallucination in Large Language Models, ACL-Findings 2024 [Present]
W10	10/26	Model Interpretability, Model Steering	Scaling and evaluating sparse autoencoders, ICLR 2025 Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation, ICLR 2025 Steering Llama 2 via Contrastive Activation Addition, ACL 2024 Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models, arXiv 2026 [Present]
	10/28	Model Editing, Model Unlearning	Locating and Editing Factual Associations in GPT, NeurIPS 2022 AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models, ICLR 2025 Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning, COLM 2024 LLM Unlearning via Neural Activation Redirection, NeurIPS 2025 [Present]
W11	11/2	Vision-Language Alignment	When and why vision-language models behave like bags-of-words, and what to do about it?, ICLR 2023 What's "up" with vision-language models? Investigating their struggle with spatial reasoning, EMNLP 2023 Hidden in plain sight: VLMs overlook their visual representations, COLM 2025 Seeing but Not Believing: Probing the Disconnect Between Visual Attention and Answer Correctness in VLMs, ICLR 2026 [Present]
	11/4	Multimodal Reasoning	V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs, CVPR 2024 Retrieval-Augmented Perception: High-Resolution Image Perception Meets Visual RAG, ICML 2025 CogCoM: A Visual Language Model with Chain-of-Manipulations Reasoning, ICLR 2025 Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space, arXiv 2025 [Present]
	11/5	Midterm Report Due
W12	11/9	Agents, Model Memory	Toolformer: Language Models Can Teach Themselves to Use Tools, NeurIPS 2023 ReAct: Synergizing Reasoning and Acting in Language Models, ICLR 2023 MemoryBank: Enhancing Large Language Models with Long-Term Memory, AAAI 2025 A-MEM: Agentic Memory for LLM Agents, NeurIPS 2025 [Present]
	11/11	Long-Context Understanding	Lost in the Middle: How Language Models Use Long Contexts, TACL 2023 Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization, ACL-Findings 2024 LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models, NAACL 2024 Efficient Streaming Language Models with Attention Sinks, ICLR 2024 [Present]
W13	11/16	Multilingual Models	Cross-Lingual Ability of Multilingual BERT: An Empirical Study, ICLR 2020 Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models, ACL 2024 Blessing of Multilinguality: A Systematic Analysis of Multilingual In-Context Learning, ACL-Findings 2025 How do Large Language Models Handle Multilingualism?, NeurIPS 2024 [Present]
	11/18	Non-Autoregressive Generation	Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads, ICML 2024 Syntactically Supervised Transformers for Faster Neural Machine Translation, ACL 2019 Large Language Diffusion Models, NeurIPS 2025 Insertion Transformer: Flexible Sequence Generation via Insertion Operations, ICML 2019 [Present]
W14	11/23	Invited Talk (Remote)
	11/25	Reading day (No Class)
W15	11/30	Final Presentations (Remote)
	12/2	Final Presentations (Remote)
	12/6	Final Report Due