Soft Prompts for Evaluation: Measuring Conditional Distance of Capabilities

• URL: http://arxiv.org/abs/2505.14943v1
• Date: Tue, 20 May 2025 22:02:53 GMT
• Title: Soft Prompts for Evaluation: Measuring Conditional Distance of Capabilities
• Authors: Ross Nordby,
• Abstract summary: This paper introduces an approach using optimized input embeddings, or'soft prompts,' as a metric of conditional distance between a model and a target behavior.<n>An evaluation framework using soft prompts is demonstrated in natural language, chess, and pathfinding.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: To help evaluate and understand the latent capabilities of language models, this paper introduces an approach using optimized input embeddings, or 'soft prompts,' as a metric of conditional distance between a model and a target behavior. The technique aims to facilitate latent capability discovery as a part of automated red teaming/evaluation suites and to provide quantitative feedback about the accessibility of potentially concerning behaviors in a way that may scale to powerful future models, including those which may otherwise be capable of deceptive alignment. An evaluation framework using soft prompts is demonstrated in natural language, chess, and pathfinding, and the technique is extended with generalized conditional soft prompts to aid in constructing task evaluations.

Related papers

• Stochastic Encodings for Active Feature Acquisition [100.47043816019888]
  Active Feature Acquisition is an instance-wise, sequential decision making problem.<n>The aim is to dynamically select which feature to measure based on current observations, independently for each test instance.<n>Common approaches either use Reinforcement Learning, which experiences training difficulties, or greedily maximize the conditional mutual information of the label and unobserved features, which makes myopic.<n>We introduce a latent variable model, trained in a supervised manner. Acquisitions are made by reasoning about the features across many possible unobserved realizations in a latent space.
  arXiv  Detail & Related papers  (2025-08-03T23:48:46Z)
• Evaluating SAE interpretability without explanations [0.7234862895932991]
  We adapt existing methods to assess the interpretability of sparse coders, with the advantage that they do not require generating natural language explanations as an intermediate step.<n>We compare the scores produced by our interpretability metrics with human evaluations across similar tasks and varying setups, offering suggestions for the community on improving the evaluation of these techniques.
  arXiv  Detail & Related papers  (2025-07-11T10:31:53Z)
• An Iterative Feedback Mechanism for Improving Natural Language Class Descriptions in Open-Vocabulary Object Detection [0.08974531206817744]
  We present an approach for improving non-technical users' natural language text descriptions of their desired targets of interest.<n>We quantify the improvement that our feedback mechanism provides by demonstrating performance with multiple publicly-available open-vocabulary object detection models.
  arXiv  Detail & Related papers  (2025-03-21T16:34:04Z)
• Collaborative Instance Object Navigation: Leveraging Uncertainty-Awareness to Minimize Human-Agent Dialogues [54.81155589931697]
  Collaborative Instance object Navigation (CoIN) is a new task setting where the agent actively resolve uncertainties about the target instance.<n>We propose a novel training-free method, Agent-user Interaction with UncerTainty Awareness (AIUTA)<n>First, upon object detection, a Self-Questioner model initiates a self-dialogue within the agent to obtain a complete and accurate observation description.<n>An Interaction Trigger module determines whether to ask a question to the human, continue or halt navigation.
  arXiv  Detail & Related papers  (2024-12-02T08:16:38Z)
• Pointwise Mutual Information as a Performance Gauge for Retrieval-Augmented Generation [78.28197013467157]
  We show that the pointwise mutual information between a context and a question is an effective gauge for language model performance.<n>We propose two methods that use the pointwise mutual information between a document and a question as a gauge for selecting and constructing prompts that lead to better performance.
  arXiv  Detail & Related papers  (2024-11-12T13:14:09Z)
• SCENE: Evaluating Explainable AI Techniques Using Soft Counterfactuals [0.0]
  This paper introduces SCENE (Soft Counterfactual Evaluation for Natural language Explainability), a novel evaluation method. By focusing on token-based substitutions, SCENE creates contextually appropriate and semantically meaningful Soft Counterfactuals. SCENE provides valuable insights into the strengths and limitations of various XAI techniques.
  arXiv  Detail & Related papers  (2024-08-08T16:36:24Z)
• Automatic Generation of Behavioral Test Cases For Natural Language Processing Using Clustering and Prompting [6.938766764201549]
  This paper introduces an automated approach to develop test cases by exploiting the power of large language models and statistical techniques. We analyze the behavioral test profiles across four different classification algorithms and discuss the limitations and strengths of those models.
  arXiv  Detail & Related papers  (2024-07-31T21:12:21Z)
• Token-Level Adversarial Prompt Detection Based on Perplexity Measures and Contextual Information [67.78183175605761]
  Large Language Models are susceptible to adversarial prompt attacks. This vulnerability underscores a significant concern regarding the robustness and reliability of LLMs. We introduce a novel approach to detecting adversarial prompts at a token level.
  arXiv  Detail & Related papers  (2023-11-20T03:17:21Z)
• FIND: A Function Description Benchmark for Evaluating Interpretability Methods [86.80718559904854]
  This paper introduces FIND (Function INterpretation and Description), a benchmark suite for evaluating automated interpretability methods. FIND contains functions that resemble components of trained neural networks, and accompanying descriptions of the kind we seek to generate. We evaluate methods that use pretrained language models to produce descriptions of function behavior in natural language and code.
  arXiv  Detail & Related papers  (2023-09-07T17:47:26Z)
• Towards explainable evaluation of language models on the semantic similarity of visual concepts [0.0]
  We examine the behavior of high-performing pre-trained language models, focusing on the task of semantic similarity for visual vocabularies. First, we address the need for explainable evaluation metrics, necessary for understanding the conceptual quality of retrieved instances. Secondly, adversarial interventions on salient query semantics expose vulnerabilities of opaque metrics and highlight patterns in learned linguistic representations.
  arXiv  Detail & Related papers  (2022-09-08T11:40:57Z)
• FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment [93.09267863425492]
  We argue that understanding both high-level semantics and internal temporal structures of actions in competitive sports videos is the key to making predictions accurate and interpretable. We construct a new fine-grained dataset, called FineDiving, developed on diverse diving events with detailed annotations on action procedures.
  arXiv  Detail & Related papers  (2022-04-07T17:59:32Z)
• A Diagnostic Study of Explainability Techniques for Text Classification [52.879658637466605]
  We develop a list of diagnostic properties for evaluating existing explainability techniques. We compare the saliency scores assigned by the explainability techniques with human annotations of salient input regions to find relations between a model's performance and the agreement of its rationales with human ones.
  arXiv  Detail & Related papers  (2020-09-25T12:01:53Z)
• How To Evaluate Your Dialogue System: Probe Tasks as an Alternative for Token-level Evaluation Metrics [47.20761880464552]
  generative dialogue modeling is widely seen as a language modeling task. The task demands an agent to have a complex natural language understanding of its input text to carry a meaningful interaction with an user. The automatic metrics used evaluate the quality of the generated text as a proxy to the holistic interaction of the agent.
  arXiv  Detail & Related papers  (2020-08-24T13:28:35Z)

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.