Research desk

The papers behind how we build

An annotated reading list. Every entry is credited to its original authors, with a note on what it changes once the idea meets a real system.

22 entries · RSS feed

All entries

Newest Oldest A to Z

All Foundations3 Retrieval & RAG4 Reasoning5 Agents & Tool Use6 Adaptation3 Alignment3 Evaluation5

Any 20239 20226 20212 20203 20181 20171

6 entries

2022PreprintCurated
Constitutional AI: Harmlessness from AI Feedback
Bai et al.
Trains a model to critique and revise its own outputs against a written set of principles, then learns from the revised outputs. The aim is a helpful assistant that can explain why it declined, rather than one that simply refuses.
Alignment
arXiv
2022PreprintCurated
Holistic Evaluation of Language Models
Liang et al.
Argues that accuracy alone is a misleading summary of a language model, and evaluates a set of models across many scenarios and many metrics at once, including calibration, robustness, fairness and efficiency, so the trade-offs stay visible.
Evaluation
arXiv
2022ICLR 2023PublishedCurated
ReAct: Synergizing Reasoning and Acting in Language Models
Yao et al.
Interleaves verbal reasoning traces with tool actions, so the model thinks about what to do next, does it, then reasons about what came back. The reasoning trace also becomes an auditable record of why the agent took each step.
Agents & Tool Use Reasoning
arXiv
2022ICLR 2023PublishedCurated
Self-Consistency Improves Chain of Thought Reasoning in Language Models
Wang et al.
Samples several independent reasoning paths for the same question and takes the most common answer, instead of trusting a single greedy chain. The intuition is that a correct derivation can be reached many ways while a wrong one is usually reached once.
Reasoning
arXiv
2022NeurIPS 2022PublishedCurated
Training Language Models to Follow Instructions with Human Feedback
Ouyang et al.
Fine-tunes language models on human demonstrations and then on human preference comparisons collected through reinforcement learning. The paper is the origin of the RLHF pipeline that produced the first widely used instruction-following assistants.
Alignment
arXiv
2022NeurIPS 2022PublishedCurated
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Wei et al.
Shows that asking a model to write out intermediate reasoning steps before answering substantially improves multi-step arithmetic, commonsense and symbolic reasoning, and that the behaviour appears without any fine-tuning at sufficient model scale.
Reasoning
arXiv

Browse by topic

Foundations

The architectures and pre-training results everything else stands on.

3 entries

Retrieval & RAG

Grounding a model in documents you actually own.

4 entries

Reasoning

Getting a model to show its work, and checking the work.

5 entries

Agents & Tool Use

Models that call tools, hold state, and finish multi-step jobs.

6 entries

Adaptation

Changing what a model does without retraining all of it.

3 entries

Alignment

Steering outputs toward what a person would accept.

3 entries

Evaluation

How you know it works before a customer finds out it does not.

5 entries

Loading research entries

Research desk

The papers behind how we build

An annotated reading list. Every entry is credited to its original authors, with a note on what it changes once the idea meets a real system.

22 entries · RSS feed

All entries

Newest Oldest A to Z

All Foundations3 Retrieval & RAG4 Reasoning5 Agents & Tool Use6 Adaptation3 Alignment3 Evaluation5

Any 20239 20226 20212 20203 20181 20171

6 entries

2022PreprintCurated
Constitutional AI: Harmlessness from AI Feedback
Bai et al.
Trains a model to critique and revise its own outputs against a written set of principles, then learns from the revised outputs. The aim is a helpful assistant that can explain why it declined, rather than one that simply refuses.
Alignment
arXiv
2022PreprintCurated
Holistic Evaluation of Language Models
Liang et al.
Argues that accuracy alone is a misleading summary of a language model, and evaluates a set of models across many scenarios and many metrics at once, including calibration, robustness, fairness and efficiency, so the trade-offs stay visible.
Evaluation
arXiv
2022ICLR 2023PublishedCurated
ReAct: Synergizing Reasoning and Acting in Language Models
Yao et al.
Interleaves verbal reasoning traces with tool actions, so the model thinks about what to do next, does it, then reasons about what came back. The reasoning trace also becomes an auditable record of why the agent took each step.
Agents & Tool Use Reasoning
arXiv
2022ICLR 2023PublishedCurated
Self-Consistency Improves Chain of Thought Reasoning in Language Models
Wang et al.
Samples several independent reasoning paths for the same question and takes the most common answer, instead of trusting a single greedy chain. The intuition is that a correct derivation can be reached many ways while a wrong one is usually reached once.
Reasoning
arXiv
2022NeurIPS 2022PublishedCurated
Training Language Models to Follow Instructions with Human Feedback
Ouyang et al.
Fine-tunes language models on human demonstrations and then on human preference comparisons collected through reinforcement learning. The paper is the origin of the RLHF pipeline that produced the first widely used instruction-following assistants.
Alignment
arXiv
2022NeurIPS 2022PublishedCurated
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Wei et al.
Shows that asking a model to write out intermediate reasoning steps before answering substantially improves multi-step arithmetic, commonsense and symbolic reasoning, and that the behaviour appears without any fine-tuning at sufficient model scale.
Reasoning
arXiv