lisaalaz / papers

A collection of summaries of the ML and NLP papers I'm reading.

A collection of short summaries of ML and NLP papers.

Strategic planning and reasoning

• Exploring and Benchmarking the Planning Capabilities of Large Language Models (Bohnet et al., 2024)
• Let's Verify Step by Step (Lightman et al., 2023)
• Learning to Reason and Memorize with Self-Notes (Lanchantin et al., 2023)
• Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution (Fernando et al., 2023)
• Reflexion: Language Agents with Verbal Reinforcement Learning (Shinn et al., 2023)
• Tree of Thoughts: Deliberate Problem Solving with Large Language Models (Yao et al., 2023)
• Reasoning with Language Model is Planning with World Model (Hao et al., 2023)
• Least-to-Most Prompting Enables Complex Reasoning in Large Language Models (Zhou et al., 2023)

LLMs with tools

• ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings (Hao et al., 2023)
• Toolformer: Language Models Can Teach Themselves to Use Tools (Schick et al., 2023)
• ViperGPT: Visual Inference via Python Execution for Reasoning (Surís et al., 2023)
• Gorilla: Large Language Model Connected with Massive APIs (Patil et al., 2023)

Calibration/robustness

• PromptBench: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts (Zhu et al., 2023)

LVLMs

• PaLI: A Jointly-Scaled Multilingual Language-Image Model (Chen et al., 2022)
• KAT: A Knowledge Augmented Transformer for Vision-and-Language (Gui et al., 2022)

Retrieval-augmented generation

• Improving Language Models by Retrieving from Trillions of Tokens (Borgeaud et al., 2021)
• Generalization through Memorization: Nearest Neighbor Language Models (Khandelwal et al., 2020)

Target-guiding in open-ended conversation

• Target-Guided Dialogue Response Generation Using Commonsense and Data Augmentation (Gupta et al., 2022)
• Dynamic Knowledge Routing Network For Target-Guided Open-Domain Conversation (Qin et al., 2020)
• Target-Guided Open-Domain Conversation (Tang et al., 2019)

Attributed LMs

• Attributed QA: Evaluation and Modeling for Attributed Large Language Models (Bohnet et al., 2023)

Knowledge graphs

• HEAL: A Knowledge Graph for Distress Management Conversations (Welivita and Pu, 2022)

Datasets

• ANNO-MI: A Dataset of Expert-Annotated Counselling Dialogues (Wu et al., 2022)
• Towards Emotional Support Dialog Systems (Liu et al., 2021)
• Event2Mind: Commonsense Inference on Events, Intents, and Reactions (Rashkin et al., 2019)