Large language models (LLMs) have become an important semantic infrastructure for modern recommender systems. A prevailing paradigm integrates LLM-derived semantic embeddings with collaborative representations via representation alignment, implicitly assuming that the two views encode a shared latent entity and that stronger alignment yields better results. We formalize this assumption as the global low-complexity alignment hypothesis and argue that it is stronger than necessary and often structurally mismatched with real-world recommendation settings. We propose a complementary perspective in which semantic and collaborative representations are treated as partially shared yet fundamentally heterogeneous views, each containing both shared and view-specific factors. Under this shared-plus-private latent structure, enforcing global geometric alignment may distort local structure, suppress view-specific signals, and reduce informational diversity. To support this perspective, we develop complementarity-aware diagnostics that quantify overlap, unique-hit contribution, and theoretical fusion upper bounds. Empirical analyses on sparse recommendation benchmarks reveal low item-level agreement between semantic and collaborative views and substantial oracle fusion gains, indicating strong complementarity. Furthermore, controlled alignment probes show that low-capacity mappings capture only shared components and fail to recover full collaborative geometry, especially under distribution shift. These findings suggest that alignment should not be treated as the default integration principle. We advocate a shift from alignment-centric modeling to complementarity fusion-centric, complementarity-aware design, where shared factors are selectively integrated while private signals are preserved. This reframing provides a principled foundation for the next generation of LLM-enhanced recommender systems.

Non-compositional expressions present a substantial challenge for natural language processing (NLP) systems, necessitating more intricate processing compared to general language tasks, even with large pre-trained language models.Their non-compositional nature and limited availability of data resources further compound the difficulties in accurately learning their representations.This paper addresses both of these challenges.By leveraging contrastive learning techniques to build improved representations it tackles the non-compositionality challenge.Additionally, we propose a dynamic curriculum learning framework specifically designed to take advantage of the scarce available data for modeling non-compositionality.Our framework employs an easy-to-hard learning strategy, progressively optimizing the model's performance by effectively utilizing available training data.Moreover, we integrate contrastive learning into the curriculum learning approach to maximize its benefits.Experimental results demonstrate the gradual improvement in the model's performance on idiom usage recognition and metaphor detection tasks.Our evaluation encompasses six datasets, consistently affirming the effectiveness of the proposed framework.Our models available at

Idiomatic expression (IE) processing and comprehension have challenged pre-trained language models (PTLMs) because their meanings are non-compositional.Unlike prior works that enable IE comprehension through finetuning PTLMs with sentences containing IEs, in this work, we construct IEKG, a commonsense knowledge graph for figurative interpretations of IEs.This extends the established ATOMIC 20 20 (Hwang et al., 2021) graph, converting PTLMs into knowledge models (KMs) that encode and infer commonsense knowledge related to IE use.Experiments show that various PTLMs can be converted into KMs with IEKG.We verify the quality of IEKG and the ability of the trained KMs with automatic and human evaluation.Through applications in natural language understanding, we show that a PTLM injected with knowledge from IEKG exhibits improved IE comprehension ability and can generalize to IEs unseen during training.

Idiomatic expressions (IEs) play an essential role in natural language. In this paper, we study the task of idiomatic sentence paraphrasing (ISP), which aims to paraphrase a sentence with an IE by replacing the IE with its literal paraphrase. The lack of large-scale corpora with idiomatic-literal parallel sentences is a primary challenge for this task, for which we consider two separate solutions. First, we propose an unsupervised approach to ISP, which leverages an IE's contextual information and definition and does not require a parallel sentence training set. Second, we propose a weakly supervised approach using back-translation to jointly perform paraphrasing and generation of sentences with IEs to enlarge the small-scale parallel sentence training dataset. Other significant derivatives of the study include a model that replaces a literal phrase in a sentence with an IE to generate an idiomatic expression and a large scale parallel dataset with idiomatic/literal sentence pairs. The effectiveness of the proposed solutions compared to competitive baselines is seen in the relative gains of over 5.16 points in BLEU, over 8.75 points in METEOR, and over 19.57 points in SARI when the generated sentences are empirically validated on a parallel dataset using automatic and manual evaluations. We demonstrate the practical utility of ISP as a preprocessing step in En-De machine translation.

This paper focuses on paraphrase generation, which is a widely studied natural language generation task in NLP.With the development of neural models, paraphrase generation research has exhibited a gradual shift to neural methods in the recent years.This has provided architectures for contextualized representation of an input text and generating fluent, diverse and human-like paraphrases.This paper surveys various approaches to paraphrase generation with a main focus on neural methods.

Consistency of learning behaviors is known to play an important role in learners’ engagement in a course and impact their learning outcomes. Despite significant advances in the area of learning analytics (LA) in measuring various self-regulated learning behaviors, using LA to measure consistency of online course engagement patterns remains largely unexplored. This study focuses on modeling consistency of learners in online courses to address this research gap. Toward this, we propose a novel unsupervised algorithm that combines sequence pattern mining and ideas from information retrieval with a clustering algorithm to first extract engagement patterns of learners, represent learners in a vector space of these patterns and finally group them into groups with similar consistency levels. Using clickstream data recorded in a popular learning management system over two offerings of a STEM course, we validate our proposed approach to detect learners that are inconsistent in their behaviors. We find that our method not only groups learners by consistency levels, but also provides reliable instructor support at an early stage in a course.

Recommender systems usually make personalized recommendation for users by analyzing interaction ratings between users and items. In plenty of application domains, some implicit feedback, content text, and other additional auxiliary information are widely used for improving the performance of recommendation. Memory-based collaborative filtering approaches that are widely used like matrix factorization (MF) predicts a personalized ranking for an individual user by leveraging latent factor models to handle common problems in recommender systems. However, most of previous MF methods adopt only explicit ratings to make personalized recommendation, ignoring the importance of implicit feedback on both users and items in-formation. Latent factor model can be easily extended with content text by mapping text information into factors, therefore we propose an approach by using neural networks to acquire the latent factors. Meanwhile, recurrent neural networks (RNNs) are applied to convert the textual data to an auxiliary factor feature to promote the representation of items. The experimental results prove that our model is effective on two benchmark datasets, outperforming some state-of-art approaches.