|
- Counterfactual Debiasing for Fact Verification - OpenReview
016 namely CLEVER, which is augmentation-free 017 and mitigates biases on the inference stage 018 Specifically, we train a claim-evidence fusion 019 model and a claim-only model independently 020 Then, we obtain the final prediction via sub-021 tracting output of the claim-only model from 022 output of the claim-evidence fusion model,
- Measuring Mathematical Problem Solving With the MATH Dataset
To find the limits of Transformers, we collected 12,500 math problems While a three-time IMO gold medalist got 90%, GPT-3 models got ~5%, with accuracy increasing slowly
- Weakly-Supervised Affordance Grounding Guided by Part-Level. . .
In this work, we focus on the task of weakly supervised affordance grounding, where a model is trained to identify affordance regions on objects using human-object interaction images and egocentric object images without dense labels
- Large Language Models are Human-Level Prompt Engineers
We propose an algorithm for automatic instruction generation and selection for large language models with human level performance
- Reasoning of Large Language Models over Knowledge Graphs with. . .
While large language models (LLMs) have made significant progress in processing and reasoning over knowledge graphs, current methods suffer from a high non-retrieval rate
- Training Large Language Model to Reason in a Continuous . . . - OpenReview
Large language models are restricted to reason in the “language space”, where they typically express the reasoning process with a chain-of-thoughts (CoT) to solve a complex reasoning problem
- LLMOPT: Learning to Define and Solve General Optimization Problems. . .
Optimization problems are prevalent across various scenarios Formulating and then solving optimization problems described by natural language often requires highly specialized human expertise, which could block the widespread application of optimization-based decision making
- Thieves on Sesame Street! Model Extraction of BERT-based APIs
Finally, we study two defense strategies against model extraction—membership classification and API watermarking—which while successful against some adversaries can also be circumvented by more clever ones
|
|
|