allenai / understanding_mcqaLinks
Code for the arXiv preprint "Answer, Assemble, Ace: Understanding How Transformers Answer Multiple Choice Questions"
☆14Updated last month
Alternatives and similar repositories for understanding_mcqa
Users that are interested in understanding_mcqa are comparing it to the libraries listed below
Sorting:
- ⚓️ Repository for the "Thought Anchors: Which LLM Reasoning Steps Matter?" paper.☆76Updated 3 weeks ago
- The repository contains the code and dataset for the Socratic Debugging task which is a novel task for Socratically Questioning Novice De…☆18Updated last year
- A toolkit for describing model features and intervening on those features to steer behavior.☆198Updated 10 months ago
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆90Updated last year
- Repository for the paper Stream of Search: Learning to Search in Language☆150Updated 7 months ago
- Scalable Meta-Evaluation of LLMs as Evaluators☆42Updated last year
- ☆29Updated last year
- Framework and toolkits for building and evaluating collaborative agents that can work together with humans.☆97Updated 5 months ago
- 👻 Code and benchmark for our EMNLP 2023 paper - "FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactions"☆55Updated last year
- Implementation of the paper: "AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?"☆62Updated 9 months ago
- Reasoning by Communicating with Agents☆30Updated 4 months ago
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆146Updated this week
- Code of ICLR paper: https://openreview.net/forum?id=-cqvvvb-NkI☆94Updated 2 years ago
- Dataset and evaluation suite enabling LLM instruction-following for scientific literature understanding.☆42Updated 5 months ago
- Verifiers for LLM Reinforcement Learning☆72Updated 4 months ago
- ☆100Updated last year
- Code for In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering☆185Updated 7 months ago
- Automated Qualitative Analysis of LLMs (ICLR 2025)☆45Updated 2 months ago
- Evaluating the Moral Beliefs Encoded in LLMs☆28Updated 8 months ago
- ☆91Updated last year
- [ICML 2025] Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples☆105Updated last month
- ☆52Updated 10 months ago
- Interaction-first method for generating demonstrations for web-agents on any website☆48Updated 4 months ago
- [NeurIPS 2024] Knowledge Circuits in Pretrained Transformers☆155Updated 6 months ago
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks☆47Updated 9 months ago
- ☆46Updated 5 months ago
- augmented LLM with self reflection☆131Updated last year
- ☆77Updated 7 months ago
- ☆190Updated 4 months ago
- DialOp: Decision-oriented dialogue environments for collaborative language agents☆109Updated 9 months ago