A Formal Language Approach to Explaining RNNs

• URL: http://arxiv.org/abs/2006.07292v1
• Date: Fri, 12 Jun 2020 16:17:53 GMT
• Title: A Formal Language Approach to Explaining RNNs
• Authors: Bishwamittra Ghosh and Daniel Neider
• Abstract summary: This paper presents LEXR, a framework for explaining the decision making of recurrent neural networks (RNNs) using a formal description language called Linear Temporal Logic (LTL) We show that LEXR's explanations are more accurate and easier-to-understand than the ones generated by recent algorithms that extract deterministic finite automata from RNNs.
• Score: 6.624726878647541
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper presents LEXR, a framework for explaining the decision making of recurrent neural networks (RNNs) using a formal description language called Linear Temporal Logic (LTL). LTL is the de facto standard for the specification of temporal properties in the context of formal verification and features many desirable properties that make the generated explanations easy for humans to interpret: it is a descriptive language, it has a variable-free syntax, and it can easily be translated into plain English. To generate explanations, LEXR follows the principle of counterexample-guided inductive synthesis and combines Valiant's probably approximately correct learning (PAC) with constraint solving. We prove that LEXR's explanations satisfy the PAC guarantee (provided the RNN can be described by LTL) and show empirically that these explanations are more accurate and easier-to-understand than the ones generated by recent algorithms that extract deterministic finite automata from RNNs.

Related papers

• Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations [54.17275171325324]
  We present a counterexample to the Linear Representation Hypothesis (LRH) When trained to repeat an input token sequence, neural networks learn to represent the token at each position with a particular order of magnitude, rather than a direction. These findings strongly indicate that interpretability research should not be confined to the LRH.
  arXiv  Detail & Related papers  (2024-08-20T15:04:37Z)
• Inductive Learning of Logical Theories with LLMs: A Complexity-graded Analysis [9.865771016218549]
  This work presents a novel systematic methodology to analyse the capabilities and limitations of Large Language Models (LLMs) The analysis is complexity-graded w.r.t. rule dependency structure, allowing quantification of specific inference challenges on LLM performance.
  arXiv  Detail & Related papers  (2024-08-15T16:41:00Z)
• Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Proving [13.485604499678262]
  This paper investigates the verification and refinement of natural language explanations through the integration of Large Language Models (LLMs) and Theorem Provers (TPs) We present a neuro-symbolic framework, named Explanation-Refiner, that integrates TPs with LLMs to generate and formalise explanatory sentences. In turn, the TP is employed to provide formal guarantees on the logical validity of the explanations and to generate feedback for subsequent improvements.
  arXiv  Detail & Related papers  (2024-05-02T15:20:01Z)
• Neuro-Symbolic Integration Brings Causal and Reliable Reasoning Proofs [95.07757789781213]
  Two lines of approaches are adopted for complex reasoning with LLMs. One line of work prompts LLMs with various reasoning structures, while the structural outputs can be naturally regarded as intermediate reasoning steps. The other line of work adopt LLM-free declarative solvers to do the reasoning task, rendering higher reasoning accuracy but lacking interpretability due to the black-box nature of the solvers. We present a simple extension to the latter line of work. Specifically, we showcase that the intermediate search logs generated by Prolog interpreters can be accessed and interpreted into human-readable reasoning.
  arXiv  Detail & Related papers  (2023-11-16T11:26:21Z)
• Recurrent Neural Language Models as Probabilistic Finite-state Automata [66.23172872811594]
  We study what classes of probability distributions RNN LMs can represent. We show that simple RNNs are equivalent to a subclass of probabilistic finite-state automata. These results present a first step towards characterizing the classes of distributions RNN LMs can represent.
  arXiv  Detail & Related papers  (2023-10-08T13:36:05Z)
• Advancing Regular Language Reasoning in Linear Recurrent Neural Networks [56.11830645258106]
  We study whether linear recurrent neural networks (LRNNs) can learn the hidden rules in training sequences. We propose a new LRNN equipped with a block-diagonal and input-dependent transition matrix. Experiments suggest that the proposed model is the only LRNN capable of performing length extrapolation on regular language tasks.
  arXiv  Detail & Related papers  (2023-09-14T03:36:01Z)
• Understanding Post-hoc Explainers: The Case of Anchors [6.681943980068051]
  We present a theoretical analysis of a rule-based interpretability method that highlights a small set of words to explain a text's decision. After formalizing its algorithm and providing useful insights, we demonstrate mathematically that Anchors produces meaningful results.
  arXiv  Detail & Related papers  (2023-03-15T17:56:34Z)
• Extending Logic Explained Networks to Text Classification [5.289706151390118]
  We propose LENp, improving local explanations by perturbing input words, and we test it on text classification. Our results show that (i) LENp provides better local explanations than LIME in terms of sensitivity and faithfulness, and (ii) logic explanations are more useful and user-friendly than feature scoring provided by LIME as attested by a human survey.
  arXiv  Detail & Related papers  (2022-11-04T16:12:03Z)
• Neuro-Symbolic Inductive Logic Programming with Logical Neural Networks [65.23508422635862]
  We propose learning rules with the recently proposed logical neural networks (LNN) Compared to others, LNNs offer strong connection to classical Boolean logic. Our experiments on standard benchmarking tasks confirm that LNN rules are highly interpretable.
  arXiv  Detail & Related papers  (2021-12-06T19:38:30Z)
• NSL: Hybrid Interpretable Learning From Noisy Raw Data [66.15862011405882]
  This paper introduces a hybrid neural-symbolic learning framework, called NSL, that learns interpretable rules from labelled unstructured data. NSL combines pre-trained neural networks for feature extraction with FastLAS, a state-of-the-art ILP system for rule learning under the answer set semantics. We demonstrate that NSL is able to learn robust rules from MNIST data and achieve comparable or superior accuracy when compared to neural network and random forest baselines.
  arXiv  Detail & Related papers  (2020-12-09T13:02:44Z)

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.