Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms

• URL: http://arxiv.org/abs/2403.17806v2
• Date: Mon, 15 Jul 2024 12:07:09 GMT
• Title: Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms
• Authors: Michael Hanna, Sandro Pezzelle, Yonatan Belinkov,
• Abstract summary: Edge attribution patching (EAP), gradient-based approximation to interventions, has emerged as a scalable but imperfect solution to this problem. We introduce a new method - EAP with integrated gradients (EAP-IG) - that aims to better maintain a core property of circuits: faithfulness. Our experiments demonstrate that circuits found using EAP are less faithful than those found using EAP-IG, even though both have high node overlap with circuits found previously using causal interventions.
• Score: 35.514624827207136
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Many recent language model (LM) interpretability studies have adopted the circuits framework, which aims to find the minimal computational subgraph, or circuit, that explains LM behavior on a given task. Most studies determine which edges belong in a LM's circuit by performing causal interventions on each edge independently, but this scales poorly with model size. Edge attribution patching (EAP), gradient-based approximation to interventions, has emerged as a scalable but imperfect solution to this problem. In this paper, we introduce a new method - EAP with integrated gradients (EAP-IG) - that aims to better maintain a core property of circuits: faithfulness. A circuit is faithful if all model edges outside the circuit can be ablated without changing the model's performance on the task; faithfulness is what justifies studying circuits, rather than the full model. Our experiments demonstrate that circuits found using EAP are less faithful than those found using EAP-IG, even though both have high node overlap with circuits found previously using causal interventions. We conclude more generally that when using circuits to compare the mechanisms models use to solve tasks, faithfulness, not overlap, is what should be measured.

Related papers

• Hypothesis Testing the Circuit Hypothesis in LLMs [23.71068328527293]
  We formalize a set of criteria that a circuit is hypothesized to meet and develop a suite of hypothesis tests to evaluate how well circuits satisfy them. The criteria focus on the extent to which the LLM's behavior is preserved, the degree of localization of this behavior, and whether the circuit is minimal. We find that synthetic circuits -- circuits that are hard-coded in the model -- align with the idealized properties.
  arXiv  Detail & Related papers  (2024-10-16T20:45:29Z)
• Adversarial Circuit Evaluation [1.1893676124374688]
  We evaluate three circuits found in the literature (IOI, greater-than, and docstring) in an adversarial manner. We measure the KL divergence between the full model's output and the circuit's output, calculated through resample ablation, and we analyze the worst-performing inputs.
  arXiv  Detail & Related papers  (2024-07-21T13:43:44Z)
• Transformer Circuit Faithfulness Metrics are not Robust [0.04260910081285213]
  We measure circuit 'faithfulness' by ablating portions of the model's computation. We conclude that existing circuit faithfulness scores reflect both the methodological choices of researchers as well as the actual components of the circuit. The ultimate goal of mechanistic interpretability work is to understand neural networks, so we emphasize the need for more clarity in the precise claims being made about circuits.
  arXiv  Detail & Related papers  (2024-07-11T17:59:00Z)
• Functional Faithfulness in the Wild: Circuit Discovery with Differentiable Computation Graph Pruning [14.639036250438517]
  We introduce a comprehensive reformulation of the task known as Circuit Discovery, along with DiscoGP. DiscoGP is a novel and effective algorithm based on differentiable masking for discovering circuits.
  arXiv  Detail & Related papers  (2024-07-04T09:42:25Z)
• Finding Transformer Circuits with Edge Pruning [71.12127707678961]
  We propose Edge Pruning as an effective and scalable solution to automated circuit discovery. Our method finds circuits in GPT-2 that use less than half the number of edges compared to circuits found by previous methods. Thanks to its efficiency, we scale Edge Pruning to CodeLlama-13B, a model over 100x the scale that prior methods operate on.
  arXiv  Detail & Related papers  (2024-06-24T16:40:54Z)
• Adaptive Planning Search Algorithm for Analog Circuit Verification [53.97809573610992]
  We propose a machine learning (ML) approach, which uses less simulations. We show that the proposed approach is able to provide OCCs closer to the specifications for all circuits.
  arXiv  Detail & Related papers  (2023-06-23T12:57:46Z)
• Interpretability at Scale: Identifying Causal Mechanisms in Alpaca [62.65877150123775]
  We use Boundless DAS to efficiently search for interpretable causal structure in large language models while they follow instructions. Our findings mark a first step toward faithfully understanding the inner-workings of our ever-growing and most widely deployed language models.
  arXiv  Detail & Related papers  (2023-05-15T17:15:40Z)
• DAIS: Automatic Channel Pruning via Differentiable Annealing Indicator Search [55.164053971213576]
  convolutional neural network has achieved great success in fulfilling computer vision tasks despite large computation overhead. Structured (channel) pruning is usually applied to reduce the model redundancy while preserving the network structure. Existing structured pruning methods require hand-crafted rules which may lead to tremendous pruning space.
  arXiv  Detail & Related papers  (2020-11-04T07:43:01Z)
• Unbiased Risk Estimators Can Mislead: A Case Study of Learning with Complementary Labels [92.98756432746482]
  We study a weakly supervised problem called learning with complementary labels. We show that the quality of gradient estimation matters more in risk minimization. We propose a novel surrogate complementary loss(SCL) framework that trades zero bias with reduced variance.
  arXiv  Detail & Related papers  (2020-07-05T04:19:37Z)

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.