The papers behind how we build

All entries

9 entries

1. 2023ICLR 2024PublishedCurated

   SWE-bench: Can Language Models Resolve Real-World GitHub Issues?

   Jimenez et al.

   A benchmark built from real issue reports and pull requests across popular Python repositories. A model is handed a codebase and a GitHub issue and has to produce a patch that makes the repository test suite pass, which is a far harder target than generating plausible-looking code.

   EvaluationAgents & Tool Use

   arXiv
2. 2023TACL 2024PublishedCurated

   Lost in the Middle: How Language Models Use Long Contexts

   Liu et al.

   Language models attend strongly to the beginning and end of a long context and weakly to the middle. The authors show accuracy degrading in a characteristic U-shape as the position of the relevant passage moves through the input, even in models explicitly built for long contexts.

   Retrieval & RAGEvaluation

   arXiv
3. 2023NeurIPS 2023PublishedCurated

   Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena

   Zheng et al.

   An examination of whether a strong language model can stand in for a human rater on open-ended questions. The paper introduces MT-Bench and Chatbot Arena, then measures how often model judgements agree with human preference and where they systematically go wrong.

   Evaluation

   arXiv
4. 2023NeurIPS 2023PublishedCurated

   Direct Preference Optimization: Your Language Model is Secretly a Reward Model

   Rafailov et al.

   Reformulates preference learning so the reward model can be folded into the policy in closed form. The result is a single supervised objective over preference pairs, with no separate reward model and no reinforcement learning loop.

   AlignmentAdaptation

   arXiv
5. 2023NeurIPS 2023PublishedCurated

   QLoRA: Efficient Finetuning of Quantized LLMs

   Dettmers et al.

   Backpropagates through a frozen 4-bit quantized base model into a small set of low-rank adapters. The approach brings fine-tuning of large models down to a single consumer GPU while holding quality close to full 16-bit tuning.

   Adaptation

   arXiv
6. 2023NeurIPS 2023PublishedCurated

   Tree of Thoughts: Deliberate Problem Solving with Large Language Models

   Yao et al.

   Generalises chain-of-thought into a search tree. The model proposes multiple partial solutions, evaluates them against each other, and can back out of a branch that is not working, rather than committing to one linear line of reasoning.

   ReasoningAgents & Tool Use

   arXiv
7. 2023UIST 2023PublishedCurated

   Generative Agents: Interactive Simulacra of Human Behavior

   Park et al.

   Agents that keep a natural-language memory stream, reflect over it to form higher-level conclusions, and plan their day from those conclusions. The paper studies what emerges when twenty-five such agents share a small sandbox world.

   Agents & Tool Use

   arXiv
8. 2023NeurIPS 2023PublishedCurated

   Reflexion: Language Agents with Verbal Reinforcement Learning

   Shinn et al.

   Instead of updating weights, the agent writes down what went wrong after a failed attempt and carries that reflection into the next attempt. The reflection is stored in natural language and used as additional context, so no gradient step is required.

   Agents & Tool UseReasoning

   arXiv
9. 2023NeurIPS 2023PublishedCurated

   Toolformer: Language Models Can Teach Themselves to Use Tools

   Schick et al.

   A model decides for itself when to call an external API, inserts the calls into its own training data, and keeps only the ones that actually reduce its prediction loss. No hand-written tool demonstrations are needed.

   Agents & Tool Use

   arXiv

Browse by topic