Composable Interventions for Language Models

• URL: http://arxiv.org/abs/2407.06483v1
• Date: Tue, 9 Jul 2024 01:17:44 GMT
• Title: Composable Interventions for Language Models
• Authors: Arinbjorn Kolbeinsson, Kyle O'Brien, Tianjin Huang, Shanghua Gao, Shiwei Liu, Jonathan Richard Schwarz, Anurag Vaidya, Faisal Mahmood, Marinka Zitnik, Tianlong Chen, Thomas Hartvigsen,
• Abstract summary: Test-time interventions for language models can enhance factual accuracy, mitigate harmful outputs, and improve model efficiency without costly retraining. But despite a flood of new methods, different types of interventions are largely developing independently. We introduce composable interventions, a framework to study the effects of using multiple interventions on the same language models.
• Score: 60.32695044723103
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Test-time interventions for language models can enhance factual accuracy, mitigate harmful outputs, and improve model efficiency without costly retraining. But despite a flood of new methods, different types of interventions are largely developing independently. In practice, multiple interventions must be applied sequentially to the same model, yet we lack standardized ways to study how interventions interact. We fill this gap by introducing composable interventions, a framework to study the effects of using multiple interventions on the same language models, featuring new metrics and a unified codebase. Using our framework, we conduct extensive experiments and compose popular methods from three emerging intervention categories -- Knowledge Editing, Model Compression, and Machine Unlearning. Our results from 310 different compositions uncover meaningful interactions: compression hinders editing and unlearning, composing interventions hinges on their order of application, and popular general-purpose metrics are inadequate for assessing composability. Taken together, our findings showcase clear gaps in composability, suggesting a need for new multi-objective interventions. All of our code is public: https://github.com/hartvigsen-group/composable-interventions.

Related papers

• Towards Unifying Interpretability and Control: Evaluation via Intervention [25.4582941170387]
  We propose intervention as a fundamental goal of interpretability and introduce success criteria to evaluate how well methods are able to control model behavior through interventions. We extend four popular interpretability methods--sparse autoencoders, logit lens, tuned lens, and probing--into an abstract encoder-decoder framework. We introduce two new evaluation metrics: intervention success rate and the coherence-intervention tradeoff, designed to measure the accuracy of explanations and their utility in controlling model behavior.
  arXiv  Detail & Related papers  (2024-11-07T04:52:18Z)
• Improving Language Models Meaning Understanding and Consistency by Learning Conceptual Roles from Dictionary [65.268245109828]
  Non-human-like behaviour of contemporary pre-trained language models (PLMs) is a leading cause undermining their trustworthiness. A striking phenomenon is the generation of inconsistent predictions, which produces contradictory results. We propose a practical approach that alleviates the inconsistent behaviour issue by improving PLM awareness.
  arXiv  Detail & Related papers  (2023-10-24T06:15:15Z)
• Multi-Grained Multimodal Interaction Network for Entity Linking [65.30260033700338]
  Multimodal entity linking task aims at resolving ambiguous mentions to a multimodal knowledge graph. We propose a novel Multi-GraIned Multimodal InteraCtion Network $textbf(MIMIC)$ framework for solving the MEL task.
  arXiv  Detail & Related papers  (2023-07-19T02:11:19Z)
• Learning Unseen Modality Interaction [54.23533023883659]
  Multimodal learning assumes all modality combinations of interest are available during training to learn cross-modal correspondences. We pose the problem of unseen modality interaction and introduce a first solution. It exploits a module that projects the multidimensional features of different modalities into a common space with rich information preserved.
  arXiv  Detail & Related papers  (2023-06-22T10:53:10Z)
• A Closer Look at the Intervention Procedure of Concept Bottleneck Models [18.222350428973343]
  Concept bottleneck models (CBMs) are a class of interpretable neural network models that predict the target response of a given input based on its high-level concepts. CBMs enable domain experts to intervene on the predicted concepts and rectify any mistakes at test time, so that more accurate task predictions can be made at the end. We develop various ways of selecting intervening concepts to improve the intervention effectiveness and conduct an array of in-depth analyses as to how they evolve under different circumstances.
  arXiv  Detail & Related papers  (2023-02-28T02:37:24Z)
• Revisiting Offline Compression: Going Beyond Factorization-based Methods for Transformer Language Models [7.542276054279341]
  transformer language models achieve outstanding results in many natural language processing (NLP) tasks. Their enormous size often makes them impractical on memory-constrained devices, requiring practitioners to compress them to smaller networks. In this paper, we explore offline compression methods, meaning computationally-cheap approaches that do not require further fine-tuning of the compressed model.
  arXiv  Detail & Related papers  (2023-02-08T13:36:06Z)
• Analyzing Semantic Faithfulness of Language Models via Input Intervention on Question Answering [4.799822253865053]
  We formalize a notion of semantic faithfulness, in which the semantic content of a text should causally figure in a model's inferences in question answering. We show that transformer models fail to be semantically faithful once we perform two semantic interventions: deletion intervention and negation intervention. We propose an intervention-based training regime that can mitigate the undesirable effects for deletion intervention by a significant margin.
  arXiv  Detail & Related papers  (2022-12-21T00:00:01Z)
• Learning Diverse Representations for Fast Adaptation to Distribution Shift [78.83747601814669]
  We present a method for learning multiple models, incorporating an objective that pressures each to learn a distinct way to solve the task. We demonstrate our framework's ability to facilitate rapid adaptation to distribution shift.
  arXiv  Detail & Related papers  (2020-06-12T12:23:50Z)
• Estimating the Effects of Continuous-valued Interventions using Generative Adversarial Networks [103.14809802212535]
  We build on the generative adversarial networks (GANs) framework to address the problem of estimating the effect of continuous-valued interventions. Our model, SCIGAN, is flexible and capable of simultaneously estimating counterfactual outcomes for several different continuous interventions. To address the challenges presented by shifting to continuous interventions, we propose a novel architecture for our discriminator.
  arXiv  Detail & Related papers  (2020-02-27T18:46:21Z)

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.