A Little Confidence Goes a Long Way

• URL: http://arxiv.org/abs/2408.11239v1
• Date: Tue, 20 Aug 2024 23:36:00 GMT
• Title: A Little Confidence Goes a Long Way
• Authors: John Scoville, Shang Gao, Devanshu Agrawal, Javed Qadrud-Din,
• Abstract summary: We introduce a group of related methods for binary classification tasks using probes of the hidden state activations in large language models (LLMs) Performance is on par with the largest and most advanced LLMs currently available, but requiring orders of magnitude fewer computational resources and not requiring labeled data.
• Score: 3.6371715211657243
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce a group of related methods for binary classification tasks using probes of the hidden state activations in large language models (LLMs). Performance is on par with the largest and most advanced LLMs currently available, but requiring orders of magnitude fewer computational resources and not requiring labeled data. This approach involves translating class labels into a semantically rich description, spontaneous symmetry breaking of multilayer perceptron probes for unsupervised learning and inference, training probes to generate confidence scores (prior probabilities) from hidden state activations subject to known constraints via entropy maximization, and selecting the most confident probe model from an ensemble for prediction. These techniques are evaluated on four datasets using five base LLMs.

Related papers

• Chain of Stance: Stance Detection with Large Language Models [3.528201746844624]
  Stance detection is an active task in natural language processing (NLP) We propose a new prompting method, called textitChain of Stance (CoS)
  arXiv  Detail & Related papers  (2024-08-03T16:30:51Z)
• Self-training Large Language Models through Knowledge Detection [26.831873737733737]
  Large language models (LLMs) often necessitate extensive labeled datasets and training compute to achieve impressive performance across downstream tasks. This paper explores a self-training paradigm, where the LLM autonomously curates its own labels and selectively trains on unknown data samples. Empirical evaluations demonstrate significant improvements in reducing hallucination in generation across multiple subjects.
  arXiv  Detail & Related papers  (2024-06-17T07:25:09Z)
• Security Vulnerability Detection with Multitask Self-Instructed Fine-Tuning of Large Language Models [8.167614500821223]
  We introduce MSIVD, multitask self-instructed fine-tuning for vulnerability detection, inspired by chain-of-thought prompting and LLM self-instruction. Our experiments demonstrate that MSIVD achieves superior performance, outperforming the highest LLM-based vulnerability detector baseline (LineVul) with a F1 score of 0.92 on the BigVul dataset, and 0.48 on the PreciseBugs dataset.
  arXiv  Detail & Related papers  (2024-06-09T19:18:05Z)
• Cycles of Thought: Measuring LLM Confidence through Stable Explanations [53.15438489398938]
  Large language models (LLMs) can reach and even surpass human-level accuracy on a variety of benchmarks, but their overconfidence in incorrect responses is still a well-documented failure mode. We propose a framework for measuring an LLM's uncertainty with respect to the distribution of generated explanations for an answer.
  arXiv  Detail & Related papers  (2024-06-05T16:35:30Z)
• Querying Easily Flip-flopped Samples for Deep Active Learning [63.62397322172216]
  Active learning is a machine learning paradigm that aims to improve the performance of a model by strategically selecting and querying unlabeled data. One effective selection strategy is to base it on the model's predictive uncertainty, which can be interpreted as a measure of how informative a sample is. This paper proposes the it least disagree metric (LDM) as the smallest probability of disagreement of the predicted label.
  arXiv  Detail & Related papers  (2024-01-18T08:12:23Z)
• Minimally Supervised Learning using Topological Projections in Self-Organizing Maps [55.31182147885694]
  We introduce a semi-supervised learning approach based on topological projections in self-organizing maps (SOMs) Our proposed method first trains SOMs on unlabeled data and then a minimal number of available labeled data points are assigned to key best matching units (BMU) Our results indicate that the proposed minimally supervised model significantly outperforms traditional regression techniques.
  arXiv  Detail & Related papers  (2024-01-12T22:51:48Z)
• Exploiting Low-confidence Pseudo-labels for Source-free Object Detection [54.98300313452037]
  Source-free object detection (SFOD) aims to adapt a source-trained detector to an unlabeled target domain without access to the labeled source data. Current SFOD methods utilize a threshold-based pseudo-label approach in the adaptation phase. We propose a new approach to take full advantage of pseudo-labels by introducing high and low confidence thresholds.
  arXiv  Detail & Related papers  (2023-10-19T12:59:55Z)
• An Embarrassingly Simple Approach to Semi-Supervised Few-Shot Learning [58.59343434538218]
  We propose a simple but quite effective approach to predict accurate negative pseudo-labels of unlabeled data from an indirect learning perspective. Our approach can be implemented in just few lines of code by only using off-the-shelf operations.
  arXiv  Detail & Related papers  (2022-09-28T02:11:34Z)
• Few-shot Learning via Dependency Maximization and Instance Discriminant Analysis [21.8311401851523]
  We study the few-shot learning problem, where a model learns to recognize new objects with extremely few labeled data per category. We propose a simple approach to exploit unlabeled data accompanying the few-shot task for improving few-shot performance.
  arXiv  Detail & Related papers  (2021-09-07T02:19:01Z)
• Meta-Learned Confidence for Few-shot Learning [60.6086305523402]
  A popular transductive inference technique for few-shot metric-based approaches, is to update the prototype of each class with the mean of the most confident query examples. We propose to meta-learn the confidence for each query sample, to assign optimal weights to unlabeled queries. We validate our few-shot learning model with meta-learned confidence on four benchmark datasets.
  arXiv  Detail & Related papers  (2020-02-27T10:22:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.