Adaptively profiling models with task elicitation

• URL: http://arxiv.org/abs/2503.01986v2
• Date: Tue, 20 May 2025 19:15:44 GMT
• Title: Adaptively profiling models with task elicitation
• Authors: Davis Brown, Prithvi Balehannina, Helen Jin, Shreya Havaldar, Hamed Hassani, Eric Wong,
• Abstract summary: Task elicitation finds hundreds of natural-language tasks where frontier models exhibit systematic failures.<n>We find that Sonnet 3.5 over-associates quantum computing and AGI and that o3-mini is prone to hallucination when fabrications are repeated in-context.
• Score: 29.704450391533864
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Language model evaluations often fail to characterize consequential failure modes, forcing experts to inspect outputs and build new benchmarks. We introduce task elicitation, a method that automatically builds new evaluations to profile model behavior. Task elicitation finds hundreds of natural-language tasks -- an order of magnitude more than prior work -- where frontier models exhibit systematic failures, in domains ranging from forecasting to online harassment. For example, we find that Sonnet 3.5 over-associates quantum computing and AGI and that o3-mini is prone to hallucination when fabrications are repeated in-context.

Related papers

• Self-Steering Language Models [113.96916935955842]
  DisCIPL is a method for "self-steering" language models.<n>DisCIPL uses a Planner model to generate a task-specific inference program.<n>Our work opens up a design space of highly-parallelized Monte Carlo inference strategies.
  arXiv  Detail & Related papers  (2025-04-09T17:54:22Z)
• Do Language Models Understand the Cognitive Tasks Given to Them? Investigations with the N-Back Paradigm [9.577716124021029]
  We show that GPT 3.5's declining performance on 2-back and 3-back tasks reflects a working memory capacity limit similar to humans.<n>By analyzing a range of open-source language models of varying performance levels on these tasks, we show that the poor performance is due at least in part to a limitation in task comprehension and task set maintenance.
  arXiv  Detail & Related papers  (2024-12-24T03:06:52Z)
• Unsupervised Model Diagnosis [49.36194740479798]
  This paper proposes Unsupervised Model Diagnosis (UMO) to produce semantic counterfactual explanations without any user guidance. Our approach identifies and visualizes changes in semantics, and then matches these changes to attributes from wide-ranging text sources.
  arXiv  Detail & Related papers  (2024-10-08T17:59:03Z)
• Revisiting SMoE Language Models by Evaluating Inefficiencies with Task Specific Expert Pruning [78.72226641279863]
  Sparse Mixture of Expert (SMoE) models have emerged as a scalable alternative to dense models in language modeling. Our research explores task-specific model pruning to inform decisions about designing SMoE architectures. We introduce an adaptive task-aware pruning technique UNCURL to reduce the number of experts per MoE layer in an offline manner post-training.
  arXiv  Detail & Related papers  (2024-09-02T22:35:03Z)
• SKADA-Bench: Benchmarking Unsupervised Domain Adaptation Methods with Realistic Validation On Diverse Modalities [55.87169702896249]
  Unsupervised Domain Adaptation (DA) consists of adapting a model trained on a labeled source domain to perform well on an unlabeled target domain with some data distribution shift.<n>We present a complete and fair evaluation of existing shallow algorithms, including reweighting, mapping, and subspace alignment.<n>Our benchmark highlights the importance of realistic validation and provides practical guidance for real-life applications.
  arXiv  Detail & Related papers  (2024-07-16T12:52:29Z)
• OLMES: A Standard for Language Model Evaluations [64.85905119836818]
  OLMES is a documented, practical, open standard for reproducible language model evaluations.<n>It supports meaningful comparisons between smaller base models that require the unnatural "cloze" formulation of multiple-choice questions.<n> OLMES includes well-considered, documented recommendations guided by results from existing literature as well as new experiments resolving open questions.
  arXiv  Detail & Related papers  (2024-06-12T17:37:09Z)
• AttributionScanner: A Visual Analytics System for Model Validation with Metadata-Free Slice Finding [29.07617945233152]
  Data slice finding is an emerging technique for validating machine learning (ML) models by identifying and analyzing subgroups in a dataset that exhibit poor performance.<n>This approach faces significant challenges, including the laborious and costly requirement for additional metadata.<n>We introduce AttributionScanner, an innovative human-in-the-loop Visual Analytics (VA) system, designed for metadata-free data slice finding.<n>Our system identifies interpretable data slices that involve common model behaviors and visualizes these patterns through an Attribution Mosaic design.
  arXiv  Detail & Related papers  (2024-01-12T09:17:32Z)
• Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning [79.53130089003986]
  Large Language Models (LLMs) have become a feasible solution for handling tasks in various domains. In this paper, we introduce how to fine-tune a LLM model that can be privately deployed for content moderation.
  arXiv  Detail & Related papers  (2023-10-05T09:09:44Z)
• Fusing Models with Complementary Expertise [42.099743709292866]
  We consider the Fusion of Experts (FoE) problem of fusing outputs of expert models with complementary knowledge of the data distribution. Our method is applicable to both discriminative and generative tasks. We extend our method to the "frugal" setting where it is desired to reduce the number of expert model evaluations at test time.
  arXiv  Detail & Related papers  (2023-10-02T18:31:35Z)
• Bring Your Own Data! Self-Supervised Evaluation for Large Language Models [52.15056231665816]
  We propose a framework for self-supervised evaluation of Large Language Models (LLMs) We demonstrate self-supervised evaluation strategies for measuring closed-book knowledge, toxicity, and long-range context dependence. We find strong correlations between self-supervised and human-supervised evaluations.
  arXiv  Detail & Related papers  (2023-06-23T17:59:09Z)
• Earning Extra Performance from Restrictive Feedbacks [41.05874087063763]
  We set up a challenge named emphEarning eXtra PerformancE from restriCTive feEDdbacks (EXPECTED) to describe this form of model tuning problems. The goal of the model provider is to eventually deliver a satisfactory model to the local user(s) by utilizing the feedbacks. We propose to characterize the geometry of the model performance with regard to model parameters through exploring the parameters' distribution.
  arXiv  Detail & Related papers  (2023-04-28T13:16:54Z)
• Variable Importance Matching for Causal Inference [73.25504313552516]
  We describe a general framework called Model-to-Match that achieves these goals. Model-to-Match uses variable importance measurements to construct a distance metric. We operationalize the Model-to-Match framework with LASSO.
  arXiv  Detail & Related papers  (2023-02-23T00:43:03Z)
• Operationalizing Specifications, In Addition to Test Sets for Evaluating Constrained Generative Models [17.914521288548844]
  We argue that the scale of generative models could be exploited to raise the abstraction level at which evaluation itself is conducted. Our recommendations are based on leveraging specifications as a powerful instrument to evaluate generation quality.
  arXiv  Detail & Related papers  (2022-11-19T06:39:43Z)
• Discover, Explanation, Improvement: An Automatic Slice Detection Framework for Natural Language Processing [72.14557106085284]
  slice detection models (SDM) automatically identify underperforming groups of datapoints. This paper proposes a benchmark named "Discover, Explain, improve (DEIM)" for classification NLP tasks. Our evaluation shows that Edisa can accurately select error-prone datapoints with informative semantic features.
  arXiv  Detail & Related papers  (2022-11-08T19:00:00Z)
• Assessing Out-of-Domain Language Model Performance from Few Examples [38.245449474937914]
  We address the task of predicting out-of-domain (OOD) performance in a few-shot fashion. We benchmark the performance on this task when looking at model accuracy on the few-shot examples. We show that attribution-based factors can help rank relative model OOD performance.
  arXiv  Detail & Related papers  (2022-10-13T04:45:26Z)
• Generalization Properties of Retrieval-based Models [50.35325326050263]
  Retrieval-based machine learning methods have enjoyed success on a wide range of problems. Despite growing literature showcasing the promise of these models, the theoretical underpinning for such models remains underexplored. We present a formal treatment of retrieval-based models to characterize their generalization ability.
  arXiv  Detail & Related papers  (2022-10-06T00:33:01Z)
• A Generative Language Model for Few-shot Aspect-Based Sentiment Analysis [90.24921443175514]
  We focus on aspect-based sentiment analysis, which involves extracting aspect term, category, and predicting their corresponding polarities. We propose to reformulate the extraction and prediction tasks into the sequence generation task, using a generative language model with unidirectional attention. Our approach outperforms the previous state-of-the-art (based on BERT) on average performance by a large margins in few-shot and full-shot settings.
  arXiv  Detail & Related papers  (2022-04-11T18:31:53Z)
• Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning [57.4036085386653]
  We show that prompt-based models for sentence pair classification tasks still suffer from a common pitfall of adopting inferences based on lexical overlap. We then show that adding a regularization that preserves pretraining weights is effective in mitigating this destructive tendency of few-shot finetuning.
  arXiv  Detail & Related papers  (2021-09-09T10:10:29Z)
• Calibrating Over-Parametrized Simulation Models: A Framework via Eligibility Set [3.862247454265944]
  We develop a framework to develop calibration schemes that satisfy rigorous frequentist statistical guarantees. We demonstrate our methodology on several numerical examples, including an application to calibration of a limit order book market simulator.
  arXiv  Detail & Related papers  (2021-05-27T00:59:29Z)
• Language Models are Few-Shot Learners [61.36677350504291]
  We show that scaling up language models greatly improves task-agnostic, few-shot performance. We train GPT-3, an autoregressive language model with 175 billion parameters, and test its performance in the few-shot setting. GPT-3 achieves strong performance on many NLP datasets, including translation, question-answering, and cloze tasks.
  arXiv  Detail & Related papers  (2020-05-28T17:29:03Z)

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.