United States

The black-box nature of neural models has motivated a line of research that aims to generate natural language rationales to explain why a model made certain predictions. Such rationale generation models, to date, have been trained on dataset-specific crowdsourced rationales, but this approach is costly and is not generalizable to new tasks and domains. In this paper, we investigate the extent to which neural models can reason about natural language rationales that explain model predictions, relying only on distant supervision with no additional annotation cost for human-written rationales. We investigate multiple ways to automatically generate rationales using pre-trained language models, neural knowledge models, and distant supervision from related tasks, and train generative models capable of composing explanatory rationales for unseen instances. We demonstrate our approach on the defeasible inference task, a nonmonotonic reasoning task in which an inference may be strengthened or weakened when new information (an update) is introduced. Our model shows promises at generating post-hoc rationales explaining why an inference is more or less likely given the additional information, however, it mostly generates trivial rationales reflecting the fundamental limitations of neural language models. Conversely, the more realistic setup of jointly predicting the update or its type and generating rationale is more challenging, suggesting an important future direction.

AAAI 2021

Learning to Rationalize for Nonmonotonic Reasoning with Distant Supervision

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair: 
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025. ACL2025continues our field’s tradition of excellence in scholarship, innovation, and inclusivity, and I am deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.* 
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to ACL 2025". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you need to log in with the **email address you registered with**. 

ACL 2025

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

technical paper

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. 

Controlling bias in training datasets is vital for ensuring equal treatment, or parity, between different groups in downstream applications. A naive solution is to transform the data so that it is statistically independent of group membership, but this may throw away too much information when a reasonable compromise between fairness and accuracy is desired. Another common approach is to limit the ability of a particular adversary who seeks to maximize parity. Unfortunately, representations produced by adversarial approaches may still retain biases as their efficacy is tied to the complexity of the adversary used during training. To this end, we theoretically establish that by limiting the mutual information between representations and protected attributes, we can assuredly control the parity of any downstream classifier. We demonstrate an effective method for controlling parity through mutual information based on contrastive information estimators and show that they outperform approaches that rely on variational bounds based on complex generative models. We test our approach on UCI Adult and Heritage Health datasets and demonstrate that our approach provides more informative representations across a range of desired parity thresholds while providing strong theoretical guarantees on the parity of any downstream algorithm.

Controllable Guarantees for Fair Outcomes via Contrastive Information Estimation

Many smartphone applications use inertial measurement units (IMUs) to sense movement, but the use of these sensors for pedestrian localization can be challenging due to their noise characteristics. Recent data-driven inertial odometry approaches have demonstrated the increasing feasibility of inertial navigation. However, they still rely upon conventional smartphone orientation estimates that they assume to be accurate, while in fact these orientation estimates can be a significant source of error. To address the problem of inaccurate orientation estimates, we present a two-stage, data-driven pipeline using a commodity smartphone that first estimates device orientations and then estimates device position. The orientation module relies on a recurrent neural network and Extended Kalman Filter to obtain orientation estimates that are used to then rotate raw IMU measurements into the appropriate reference frame. The position module then passes those measurements through another recurrent network architecture to perform localization. Our proposed method outperforms state-of-the-art methods in both orientation and position error on a large dataset we constructed that contains 20 hours of pedestrian motion across 3 buildings and 15 subjects. Code and data are available at https://github.com/KlabCMU/IDOL.

IDOL: Inertial Deep Orientation-Estimation and Localization

Graph Neural Networks (GNNs) have proven to be useful for many different practical applications. However, many existing GNN models have implicitly assumed homophily among the nodes connected in the graph, and therefore have largely overlooked the important setting of heterophily, where most connected nodes are from different classes. In this work, we propose a novel framework called CPGNN that generalizes GNNs for graphs with either homophily or heterophily. The proposed framework incorporates an interpretable compatibility matrix for modeling the heterophily or homophily level in the graph, which can be learned in an end-to-end fashion, enabling it to go beyond the assumption of strong homophily. Theoretically, we show that replacing the compatibility matrix in our framework with the identity (which represents pure homophily) reduces to GCN. Our extensive experiments demonstrate the effectiveness of our approach in more realistic and challenging experimental settings with significantly less training data compared to previous works: CPGNN variants achieve state-of-the-art results in heterophily settings with or without contextual node features, while maintaining comparable performance in homophily settings.

Graph Neural Networks with Heterophily

Recent work introduced XDP and XUP priority functions for best-first bounded-suboptimal search that do not need to perform state re-expansions as long as the search heuristic is consistent. However, that work had several limitations that are rectified here. This paper analyzes the sufficiency and necessity of the conditions used to formulate XDP and XUP. The analysis presents a simpler proof and generalizes the result in three aspects: (1) the priority function no longer has to be differentiable everywhere, (2) the quality of the solution does not have to be bounded by a constant factor, and (3) directed graphs are handled correctly. These results allow the introduction of more priority functions, such as piecewise linear functions, and more variants of bounded-suboptimal search, such as constant suboptimality. Several new priority functions are presented in this paper that, according to empirical results, can significantly outperform existing approaches including XDP.

Necessary and Sufficient Conditions for Avoiding Reopenings in Best First Suboptimal Search with General Bounding Functions

Lexical cohesion is a fundamental mechanism for text which requires a pair of words to be interpreted as a certain type of lexical relation (e.g., similarity) to understand a coherent context; we refer to such relations as the contextual lexical relation. However, work on lexical cohesion has not modeled context comprehensively in considering lexical relations due to the lack of linguistic resources. In this paper, we take initial steps to address contextual lexical relations by focusing on the contrast relation, as it is a well-known relation though it is more subtle and relatively less resourced. We present a corpus named Cont 2 Lex to make Contextual Lexical Contrast Recognition a computationally feasible task. We benchmark this task with widely-adopted semantic representations; we discover that contextual embeddings (e.g. BERT) generally outperform static embeddings (e.g. Glove), but barely go beyond 70% in accuracy performance. In addition, we ï¬nd that all embeddings perform better when CLC occurs within the same sentence, suggesting possible limitations of current computational coherence models. Another intriguing discovery is the improvement of BERT in CLC is largely attributed to its modeling of CLC word pairs co-occurring with other word repetitions. Such observations imply that the progress made in lexical coherence modeling remains relatively primitive even for semantic representations such as BERT that have been empowering numerous standard NLP tasks to approach human benchmarks. Through presenting our corpus and benchmark, we attempt to seed initial discussions and endeavors in advancing semantic representations from modeling syntactic and semantic levels to coherence and discourse levels.

Have We Solved the Hard Problem? It’s Not Easy! Contextual Lexical Contrast as a Means to Probe Neural Coherence

We propose a novel distributed user-car matching method based on a contract between users to mitigate the imbalance problem between vehicle distribution and demand in free-floating car sharing. Previous regulation methods involved an incentive system based on the predictions of origin-destination (OD) demand obtained from past usage history. However, the difficulty these methods have in obtaining accurate data limits their applicability. To overcome this drawback, we introduce contract-based coordination among drop-off and pick-up users in which an auction is conducted for drop-off users' intended drop-off locations. We theoretically analyze the proposed method regarding the upper bound of its efficiency. We also compare it with a baseline method and non-regulation scenario on a free-floating car-sharing simulator. The experimental results show that the proposed method achieves a higher social surplus than the existing method.

Contract-Based Inter-User Usage Coordination in Free-Floating Car Sharing

Post-hoc explanation methods are gaining popularity for interpreting, understanding, and debugging neural networks. Most analyses using such methods explain decisions in response to inputs drawn from the test set. However, the test set may have few 
examples that trigger some model behaviors, such as high-confidence failures or ambiguous classifications. To address these challenges, we introduce a flexible model inspection framework: Bayes-TrEx. Given a data distribution, Bayes-TrEx finds in-distribution examples which trigger a specified prediction confidence. We demonstrate several use cases of Bayes-TrEx, including revealing highly confident (mis)classifications, visualizing class boundaries via ambiguous examples, understanding novel-class extrapolation behavior, and exposing neural network overconfidence. We use Bayes-TrEx to study classifiers trained on CLEVR, MNIST, and Fashion-MNIST, and we show that this framework enables more flexible holistic model analysis than just inspecting the test set. Code and supplemental material are available at https://github.com/serenabooth/Bayes-TrEx.

Bayes-TrEx: a Bayesian Sampling Approach to Model Transparency by Example

Many widely-used causal discovery methods such as Greedy Equivalent Search (GES), although with asymptotic correctness guarantees, have been reported to produce sub-optimal solutions on finite data, or when the causal faithfulness condition is violated. The constraint-based procedure with Boolean satisfiability (SAT) solver, and the recently proposed Sparsest Permutation (SP) algorithm have shown superb performance, but currently they do not scale well. In this work, we demonstrate that optimal score-based exhaustive search is remarkably useful for causal discovery: it requires weaker conditions to guarantee asymptotic correctness, and outperforms well-known methods including PC, GES, GSP, and NOTEARS. In order to achieve scalability, we also develop an approximation algorithm for larger systems based on the  A* method, which scales up to 60+ variables and obtains better results than existing greedy algorithms such as GES, MMHC, and GSP. Our results illustrate the risk of assuming the faithfulness assumption, the advantages of exhaustive search methods, and the limitations of greedy search methods, and shed light on the computational challenges and techniques in scaling up to larger networks and handling unfaithful data.

Improving Causal Discovery by Optimal Bayesian Network Learning

Recent works within machine learning have been tackling inputs of ever increasing size, with cyber security presenting sequence classification problems of particularly extreme lengths. In the case of Windows executable malware detection, an input executable could be >=100 MB, which would translate to a time series with T=100,000,000 steps. To date, the closest approach to handling such task is MalConv --- a convolutional neural network capable of processing T=2,000,000 steps. Because the memory used by CNNs is O(T), this has prevented many from processing all executables or further extending the MalConv approach. In this work, we develop a new approach to temporal max pooling that makes the required memory invariant to the sequence length T. This makes MalConv 116x more memory efficient, and up to 25.8x faster to train, while removing the input length restrictions to MalConv. We re-invest these gains into improving the MalConv architecture by developing a new Global Channel Gating design, giving us an attention mechanism capable of learning feature interactions across 100 million time steps in an efficient manner, a capability lacked by the original MalConv approach.

Classifying Sequences of Extreme Length with Constant Memory Applied to Malware Detection

Community detection is a research hotspot in machine learning and data mining. However, most of the existing community detection methods only rely on the lower-order connectivity patterns, while ignoring the higher-order connectivity patterns, and unable to capture the building blocks of the complex network. In recent years, some community detection methods based on higher-order structures have been developed, but they mainly focus on the motif network composed of higher-order structures, which violate the original lower-order topological structure and are affected by the fragmentation issue, resulting in the deviation of community detection results. Therefore, there is still a lack of community detection methods that can effectively utilize higher-order connectivity patterns and lower-order connectivity patterns. To overcome the above limitations, this paper proposes the Hybrid-order Stochastic Block Model (HSBM) from the perspective of the generative model. Based on the classical stochastic block model, the generation of lower-order structure and higher-order structure of the network is modeled uniformly, and the original topological properties of the network are maintained while using higher-order connectivity patterns. At the same time, a heuristic algorithm for community detection is proposed to optimize the objective function. Extensive experiments on six real-world datasets show that the proposed method outperforms the existing approaches.

Downloads

Next from AAAI 2021

Controllable Guarantees for Fair Outcomes via Contrastive Information Estimation

Similar lecture

Rationales Are Not Silver Bullets: Measuring the Impact of Rationales on Model Performance and Reliability

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2021

Controllable Guarantees for Fair Outcomes via Contrastive Information Estimation

Similar lecture

Rationales Are Not Silver Bullets: Measuring the Impact of Rationales on Model Performance and Reliability

Downloads