Mixture of Hidden-Dimensions Transformer

Transformer models encounter challenges in scaling hidden dimensions efficiently, as uniformly increasing them inflates computational and memory costs while failing to emphasize the most relevant features for each token. For further understanding, we study hidden dimension sparsity and observe that trained Transformers utilize only a small fraction of token dimensions, revealing an "activation flow" pattern. Notably, there are shared sub-dimensions with sustained activation across multiple consecutive tokens and specialized sub-dimensions uniquely activated for each token. To better model token-relevant sub-dimensions, we propose MoHD (Mixture of Hidden Dimensions), a sparse conditional activation architecture. Particularly, MoHD employs shared sub-dimensions for common token features and a routing mechanism to dynamically activate specialized sub-dimensions. To mitigate potential information loss from sparsity, we design activation scaling and group fusion mechanisms to preserve activation flow. In this way, MoHD expands hidden dimensions with negligible increases in computation or parameters, efficient training and inference while maintaining performance. Evaluations across 10 NLP tasks show that MoHD surpasses Vanilla Transformers in parameter efficiency and task performance. It achieves 1.7% higher performance with 50% fewer activation parameters and 3.7% higher performance with a 3x parameter expansion at constant activation cost. MOHD offers a new perspective for scaling the model, showcasing the potential of hidden dimension sparsity to boost efficiency

MoR: Mixture of Ranks for Low-Rank Adaptation Tuning

Low-Rank Adaptation (LoRA) drives research to align its performance with full fine-tuning. However, significant challenges remain: (1) Simply increasing the rank size of LoRA does not effectively capture high-rank information, which leads to a performance bottleneck.(2) MoE-style LoRA methods substantially increase parameters and inference latency, contradicting the goals of efficient fine-tuning and ease of application. To address these challenges, we introduce Mixture of Ranks (MoR), which learns rank-specific information for different tasks based on input and efficiently integrates multi-rank information. We firstly propose a new framework that equates the integration of multiple LoRAs to expanding the rank of LoRA. Moreover, we hypothesize that low-rank LoRA already captures sufficient intrinsic information, and MoR can derive high-rank information through mathematical transformations of the low-rank components. Thus, MoR can reduces the learning difficulty of LoRA and enhances its multi-task capabilities. MoR achieves impressive results, with MoR delivering a 1.31\% performance improvement while using only 93.93\% of the parameters compared to baseline methods.

Revealing the Challenge of Detecting Character Knowledge Errors in LLM Role-Playing

Large language model (LLM) role-playing has gained widespread attention, where the authentic character knowledge is crucial for constructing realistic LLM role-playing agents. However, existing works usually overlook the exploration of LLMs' ability to detect characters' known knowledge errors (KKE) and unknown knowledge errors (UKE) while playing roles, which would lead to low-quality automatic construction of character trainable corpus. In this paper, we propose a probing dataset to evaluate LLMs' ability to detect errors in KKE and UKE. The results indicate that even the latest LLMs struggle to effectively detect these two types of errors, especially when it comes to familiar knowledge. We experimented with various reasoning strategies and propose an agent-based reasoning method, Self-Recollection and Self-Doubt (S2RD), to further explore the potential for improving error detection capabilities. Experiments show that our method effectively improves the LLMs' ability to detect error character knowledge, but it remains an issue that requires ongoing attention.

NACL: A General and Effective KV Cache Eviction Framework for LLMs at Inference Time

Large Language Models (LLMs) have ignited an innovative surge of AI applications, marking a new era of exciting possibilities equipped with extended context windows. However, hosting these models is cost-prohibitive mainly due to the extensive memory consumption of KV Cache involving long-context modeling. Despite several works proposing to evict unnecessary tokens from the KV Cache, most of them rely on the biased local statistics of accumulated attention scores and report performance using unconvincing metric like perplexity on inadequate short-text evaluation. In this paper, we propose NACL, a general framework for long-context KV cache eviction that achieves more optimal and efficient eviction in a single operation during the encoding phase. Due to NACL's efficiency, we combine more accurate attention score statistics in PROXY TOKENS EVICTION with the diversified random eviction strategy of RANDOM EVICTION, aiming to alleviate the issue of attention bias and enhance the robustness in maintaining pivotal tokens for long-context modeling tasks. Notably, our method significantly improves the performance on short- and long-text tasks by 80% and 76% respectively, reducing KV Cache by up to 50% with over 95% performance maintenance. The code is available at https: //github.com/PaddlePaddle/Research/ tree/master/NLP/ACL2024-NACL.

LoginMEA: Local-to-Global Interaction Network for Multi-modal Entity Alignment

Multi-modal entity alignment (MMEA) aims to identify equivalent entities between two multi-modal knowledge graphs (MMKGs), whose entities can be associated with relational triples and related images. Most previous studies treat the graph structure as a special modality, and fuse different modality information with separate uni-modal encoders, neglecting valuable relational associations in modalities. Other studies refine each uni-modal information with graph structures, but may introduce unnecessary relations in specific modalities. To this end, we propose a novel local-to-global interaction network for MMEA, termed as LoginMEA. Particularly, we first fuse local multi-modal interactions to generate holistic entity semantics and then refine them with global relational interactions of entity neighbors. In this design, the uni-modal information is fused adaptively, and can be refined with relations accordingly. To enrich local interactions of multi-modal entity information, we device modality weights and low-rank interactive fusion, allowing diverse impacts and element-level interactions among modalities. To capture global interactions of graph structures, we adopt relation reflection graph attention networks, which fully capture relational associations between entities. Extensive experiments demonstrate superior results of our method over 5 cross-KG or bilingual benchmark datasets, indicating the effectiveness of capturing local and global interactions.

IBMEA: Exploring Variational Information Bottleneck for Multi-modal Entity Alignment

Multi-modal entity alignment (MMEA) aims to identify equivalent entities between multi-modal knowledge graphs (MMKGs), where the entities can be associated with related images. Most existing studies integrate multi-modal information heavily relying on the automatically-learned fusion module, rarely suppressing the redundant information for MMEA explicitly. To this end, we explore variational information bottleneck for multi-modal entity alignment (IBMEA), which emphasizes the alignment-relevant information and suppresses the alignment-irrelevant information in generating entity representations. Specifically, we devise multi-modal variational encoders to generate modal-specific entity representations as probability distributions. Then, we propose four modal-specific information bottleneck regularizers, limiting the misleading clues in refining modal-specific entity representations. Finally, we propose a modal-hybrid information contrastive regularizer to integrate all the refined modal-specific representations, enhancing the entity similarity between MMKGs to achieve MMEA. We conduct extensive experiments on two cross-KG and three bilingual MMEA datasets. Experimental results demonstrate that our model consistently outperforms previous state-of-the-art methods, and also shows promising and robust performance in low-resource and high-noise data scenarios.

Optimal Transport Guided Correlation Assignment for Multimodal Entity Linking

Multimodal Entity Linking (MEL) aims to link ambiguous mentions in multimodal contexts to entities in a multimodal knowledge graph. A pivotal challenge is to fully leverage multi-element correlations between mentions and entities to bridge modality gap and enable fine-grained semantic matching. Existing methods attempt several local correlative mechanisms, relying heavily on the automatically learned attention weights, which may over-concentrate on partial correlations. To mitigate this issue, we formulate the correlation assignment problem as an optimal transport (OT) problem, and propose a novel MEL framework, namely OT-MEL, with OT-guided correlation assignment. Thereby, we exploit the correlation between multimodal features to enhance multimodal fusion, and the correlation between mentions and entities to enhance fine-grained matching. To accelerate model prediction, we further leverage knowledge distillation to transfer OT assignment knowledge to attention mechanism. Experimental results show that our model significantly outperforms previous state-of-the-art baselines and confirm the effectiveness of the OT-guided correlation assignment.

DHA: Learning Decoupled-Head Attention from Transformer Checkpoints via Adaptive Heads Fusion

Large language models (LLMs) with billions of parameters demonstrate impressive performance. However, the widely used Multi-Head Attention (MHA) in LLMs incurs substantial computational and memory costs during inference. While some efforts have optimized attention mechanisms by pruning heads or sharing parameters among heads, these methods often lead to performance degradation or necessitate substantial continued pre-training costs to restore performance. Based on the analysis of attention redundancy, we design a Decoupled-Head Attention (DHA) mechanism. DHA adaptively configures group sharing for key heads and value heads across various layers, achieving a better balance between performance and efficiency. Inspired by the observation of clustering similar heads, we propose to progressively transform the MHA checkpoint into the DHA model through linear fusion of similar head parameters step by step, retaining the parametric knowledge of the MHA checkpoint. We construct DHA models by transforming various scales of MHA checkpoints given target head budgets. Our experiments show that DHA remarkably requires a mere 0.25\% of the original model's pre-training budgets to achieve 97.6\% of performance while saving 75\% of KV cache. Compared to Group-Query Attention (GQA), DHA achieves a 5$\times$ training acceleration, a maximum of 13.93\% performance improvement under 0.01\% pre-training budget, and 4\% relative improvement under 0.05\% pre-training budget.

CDRNP: Cross-Domain Recommendation to Cold-Start Users via Neural Process

Cross-domain recommendation (CDR) has been proven as a promising way to tackle the user cold-start problem, which aims to make recommendations for users in the target domain by transferring the user preference derived from the source domain. Traditional CDR studies follow the embedding and mapping (EMCDR) paradigm, which transfers user representations from the source to target domain by learning a user-shared mapping function, neglecting the user-specific preference. Recent CDR studies attempt to learn user-specific mapping functions in meta-learning paradigm, which regards each user's CDR as an individual task, but neglects the preference correlations among users, limiting the beneficial information for user representations. Moreover, both of the paradigms neglect the explicit user-item interactions from both domains during the mapping process. To address the above issues, this paper proposes a novel CDR framework with neural process (NP), termed as CDRNP. Particularly, it develops the meta-learning paradigm to leverage user-specific preference, and further introduces a stochastic process by NP to capture the preference correlations among the overlapping and cold-start users, thus generating more powerful mapping functions by mapping the user-specific preference and common preference correlations to a predictive probability distribution. In addition, we also introduce a preference remainer to enhance the common preference from the overlapping users, and finally devises an adaptive conditional decoder with preference modulation to make prediction for cold-start users with items in the target domain. Experimental results demonstrate that CDRNP outperforms previous SOTA methods in three real-world CDR scenarios.

Adaptive Data Augmentation for Aspect Sentiment Quad Prediction

Aspect sentiment quad prediction (ASQP) aims to predict the quad sentiment elements for a given sentence, which is a critical task in the field of aspect-based sentiment analysis. However, the data imbalance issue has not received sufficient attention in ASQP task. In this paper, we divide the issue into two-folds, quad-pattern imbalance and aspect-category imbalance, and propose an Adaptive Data Augmentation (ADA) framework to tackle the imbalance issue. Specifically, a data augmentation process with a condition function adaptively enhances the tail quad patterns and aspect categories, alleviating the data imbalance in ASQP. Following previous studies, we also further explore the generative framework for extracting complete quads by introducing the category prior knowledge and syntax-guided decoding target. Experimental results demonstrate that data augmentation for imbalance in ASQP task can improve the performance, and the proposed ADA method is superior to naive data oversampling.