LLMs for Relational Reasoning: How Far are We?

Large language models (LLMs) have revolutionized many areas (e.g. natural language processing, software engineering, etc.) by achieving state-of-the-art performance on extensive downstream tasks. Aiming to achieve robust and general artificial intelligence, there has been a surge of interest in investigating the reasoning ability of the LLMs. Whereas the textual and numerical reasoning benchmarks adopted by previous works are rather shallow and simple, it is hard to conclude that the LLMs possess strong reasoning ability by merely achieving positive results on these benchmarks. Recent efforts have demonstrated that the LLMs are poor at solving sequential decision-making problems that require common-sense planning by evaluating their performance on the reinforcement learning benchmarks. In this work, we conduct an in-depth assessment of several state-of-the-art LLMs' reasoning ability based on the inductive logic programming (ILP) benchmark, which is broadly recognized as a representative and challenging measurement for evaluating logic program induction/synthesis systems as it requires inducing strict cause-effect logic to achieve robust deduction on independent and identically distributed (IID) and out-of-distribution (OOD) test samples. Our evaluations illustrate that compared with the neural program induction systems which are much smaller in model size, the state-of-the-art LLMs are much poorer in terms of reasoning ability by achieving much lower performance and generalization using either natural language prompting or truth-value matrix prompting.

Cross-View Graph Consistency Learning for Invariant Graph Representations

Graph representation learning is fundamental for analyzing graph-structured data. Exploring invariant graph representations remains a challenge for most existing graph representation learning methods. In this paper, we propose a cross-view graph consistency learning (CGCL) method that learns invariant graph representations for link prediction. First, two complementary augmented views are derived from an incomplete graph structure through a bidirectional graph structure augmentation scheme. This augmentation scheme mitigates the potential information loss that is commonly associated with various data augmentation techniques involving raw graph data, such as edge perturbation, node removal, and attribute masking. Second, we propose a CGCL model that can learn invariant graph representations. A cross-view training scheme is proposed to train the proposed CGCL model. This scheme attempts to maximize the consistency information between one augmented view and the graph structure reconstructed from the other augmented view. Furthermore, we offer a comprehensive theoretical CGCL analysis. This paper empirically and experimentally demonstrates the effectiveness of the proposed CGCL method, achieving competitive results on graph datasets in comparisons with several state-of-the-art algorithms.

Logic-guided Deep Reinforcement Learning for Stock Trading

Deep reinforcement learning (DRL) has revolutionized quantitative finance by achieving excellent performance without significant manual effort. Whereas we observe that the DRL models behave unstably in a dynamic stock market due to the low signal-to-noise ratio nature of the financial data. In this paper, we propose a novel logic-guided trading framework, termed as SYENS (Program Synthesis-based Ensemble Strategy). Different from the previous state-of-the-art ensemble reinforcement learning strategy which arbitrarily selects the best-performing agent for testing based on a single measurement, our framework proposes regularizing the model's behavior in a hierarchical manner using the program synthesis by sketching paradigm. First, we propose a high-level, domain-specific language (DSL) that is used for the depiction of the market environment and action. Then based on the DSL, a novel program sketch is introduced, which embeds human expert knowledge in a logical manner. Finally, based on the program sketch, we adopt the program synthesis by sketching a paradigm and synthesizing a logical, hierarchical trading strategy. We evaluate SYENS on the 30 Dow Jones stocks under the cash trading and the margin trading settings. Experimental results demonstrate that our proposed framework can significantly outperform the baselines with much higher cumulative return and lower maximum drawdown under both settings.

FAIRER: Fairness as Decision Rationale Alignment

Deep neural networks (DNNs) have made significant progress, but often suffer from fairness issues, as deep models typically show distinct accuracy differences among certain subgroups (e.g., males and females). Existing research addresses this critical issue by employing fairness-aware loss functions to constrain the last-layer outputs and directly regularize DNNs. Although the fairness of DNNs is improved, it is unclear how the trained network makes a fair prediction, which limits future fairness improvements. In this paper, we investigate fairness from the perspective of decision rationale and define the parameter parity score to characterize the fair decision process of networks by analyzing neuron influence in various subgroups. Extensive empirical studies show that the unfair issue could arise from the unaligned decision rationales of subgroups. Existing fairness regularization terms fail to achieve decision rationale alignment because they only constrain last-layer outputs while ignoring intermediate neuron alignment. To address the issue, we formulate the fairness as a new task, i.e., decision rationale alignment that requires DNNs' neurons to have consistent responses on subgroups at both intermediate processes and the final prediction. To make this idea practical during optimization, we relax the naive objective function and propose gradient-guided parity alignment, which encourages gradient-weighted consistency of neurons across subgroups. Extensive experiments on a variety of datasets show that our method can significantly enhance fairness while sustaining a high level of accuracy and outperforming other approaches by a wide margin.

GALOIS: Boosting Deep Reinforcement Learning via Generalizable Logic Synthesis

Despite achieving superior performance in human-level control problems, unlike humans, deep reinforcement learning (DRL) lacks high-order intelligence (e.g., logic deduction and reuse), thus it behaves ineffectively than humans regarding learning and generalization in complex problems. Previous works attempt to directly synthesize a white-box logic program as the DRL policy, manifesting logic-driven behaviors. However, most synthesis methods are built on imperative or declarative programming, and each has a distinct limitation, respectively. The former ignores the cause-effect logic during synthesis, resulting in low generalizability across tasks. The latter is strictly proof-based, thus failing to synthesize programs with complex hierarchical logic. In this paper, we combine the above two paradigms together and propose a novel Generalizable Logic Synthesis (GALOIS) framework to synthesize hierarchical and strict cause-effect logic programs. GALOIS leverages the program sketch and defines a new sketch-based hybrid program language for guiding the synthesis. Based on that, GALOIS proposes a sketch-based program synthesis method to automatically generate white-box programs with generalizable and interpretable cause-effect logic. Extensive evaluations on various decision-making tasks with complex logic demonstrate the superiority of GALOIS over mainstream baselines regarding the asymptotic performance, generalizability, and great knowledge reusability across different environments.

Unveiling Project-Specific Bias in Neural Code Models

Neural code models have introduced significant improvements over many software analysis tasks like type inference, vulnerability detection, etc. Despite the good performance of such models under the common intra-project independent and identically distributed (IID) training and validation setting, we observe that they usually fail to generalize to real-world inter-project out-of-distribution (OOD) setting. In this work, we show that such phenomenon is caused by model heavily relying on project-specific, ungeneralizable tokens like self-defined variable and function names for downstream prediction, and we formulate it as the project-specific bias learning behavior. We propose a measurement to interpret such behavior, termed as Cond-Idf, which combines co-occurrence probability and inverse document frequency to measure the level of relatedness of token with label and its project-specificness. The approximation indicates that without proper regularization with prior knowledge, model tends to leverage spurious statistical cues for prediction. Equipped with these observations, we propose a bias mitigation mechanism Batch Partition Regularization (BPR) that regularizes model to infer based on proper behavior by leveraging latent logic relations among samples. Experimental results on two deep code benchmarks indicate that BPR can improve both inter-project OOD generalization and adversarial robustness while not sacrificing accuracy on IID data.

Cross-Lingual Adaptation for Type Inference

Deep learning-based techniques have been widely applied to the program analysis tasks, in fields such as type inference, fault localization, and code summarization. Hitherto deep learning-based software engineering systems rely thoroughly on supervised learning approaches, which require laborious manual effort to collect and label a prohibitively large amount of data. However, most Turing-complete imperative languages share similar control- and data-flow structures, which make it possible to transfer knowledge learned from one language to another. In this paper, we propose cross-lingual adaptation of program analysis, which allows us to leverage prior knowledge learned from the labeled dataset of one language and transfer it to the others. Specifically, we implemented a cross-lingual adaptation framework, PLATO, to transfer a deep learning-based type inference procedure across weakly typed languages, e.g., Python to JavaScript and vice versa. PLATO incorporates a novel joint graph kernelized attention based on abstract syntax tree and control flow graph, and applies anchor word augmentation across different languages. Besides, by leveraging data from strongly typed languages, PLATO improves the perplexity of the backbone cross-programming-language model and the performance of downstream cross-lingual transfer for type inference. Experimental results illustrate that our framework significantly improves the transferability over the baseline method by a large margin.

Seismic data interpolation based on U-net with texture loss

Missing traces in acquired seismic data is a common occurrence during the collection of seismic data. Deep neural network (DNN) has shown considerable promise in restoring incomplete seismic data. However, several DNN-based approaches ignore the specific characteristics of seismic data itself, and only focus on reducing the difference between the recovered and the original signals. In this study, a novel Seismic U-net InterpolaTor (SUIT) is proposed to preserve the seismic texture information while reconstructing the missing traces. Aside from minimizing the reconstruction error, SUIT enhances the texture consistency between the recovery and the original completely seismic data, by designing a pre-trained U-Net to extract the texture information. The experiments show that our method outperforms the classic state-of-art methods in terms of robustness.

Adabot: Fault-Tolerant Java Decompiler

Reverse Engineering(RE) has been a fundamental task in software engineering. However, most of the traditional Java reverse engineering tools are strictly rule defined, thus are not fault-tolerant, which pose serious problem when noise and interference were introduced into the system. In this paper, we view reverse engineering as a machine translation task and propose a fault-tolerant Java decompiler based on machine translation models. Our model is based on attention-based Neural Machine Translation (NMT) and Transformer architectures. First, we measure the translation quality on both the redundant and purified datasets. Next, we evaluate the fault-tolerance(anti-noise ability) of our framework on test sets with different unit error probability (UEP). In addition, we compare the suitability of different word segmentation algorithms for decompilation task. Experimental results demonstrate that our model is more robust and fault-tolerant compared to traditional Abstract Syntax Tree (AST) based decompilers. Specifically, in terms of BLEU-4 and Word Error Rate (WER), our performance has reached 94.50\% and 2.65\% on the redundant test set; 92.30\% and 3.48\% on the purified test set.