Large Language Models (LLMs) have demonstrated remarkable In-Context learning (ICL) capabilities for relation extraction (RE). While ICL has shown promise in RE tasks, current approaches face challenges in example selection and utilization. These challenges stem from the misalignment between example selection methods and LLMs' inherent cognitive processing mechanisms, particularly in pattern recognition and relational reasoning. To address these limitations, we propose Counterfactual Cognitive Alignment (CCA), a novel framework that systematically enhances ICL performance in RE by aligning example selection with cognitive principles underlying human relational reasoning. The framework incorporates a cognitive-inspired counterfactual generation mechanism that creates semantically diverse yet relationally coherent examples, mirroring human "what-if" reasoning processes. Additionally, it employs a cognitive alignment approach that integrates structural identification features with semantic understanding to better align with LLMs cognitive processing patterns. Extensive experiments across multiple RE benchmarks reveal the effectiveness of our cognitive alignment approach through the synergistic integration of counterfactual reasoning and cognitively-guided selection.

Instruction tuning has emerged as an effective approach that notably improves large language models (LLMs) performance, showing particular promise in natural language generation tasks by producing more diverse, coherent, and task-relevant outputs. However, extending instruction tuning to natural language understanding (NLU) tasks presents significant challenges, primarily due to the difficulty in achieving high-precision responses and the scarcity of large-scale, high-quality instruction data necessary for effective tuning. In this work, we introduce Adversarial Noisy Instruction Tuning (ANIT) to improve NLU performance on LLMs. First, we leverage low-resource techniques to construct noisy instruction datasets. Second, we employ semantic distortion-aware techniques to quantify the intensity of noise within these instructions. Last, we devise an adversarial training method that incorporates a noise response strategy to achieve noisy instruction tuning. ANIT enhances LLMs capability to detect and accommodate semantic distortions in noisy instructions, thereby augmenting their comprehension of task objectives and ability to generate more accurate responses. We evaluate our approach across diverse noisy instructions and semantic distortion quantification methods on multiple NLU tasks. Comprehensive empirical results demonstrate that our method consistently outperforms existing approaches across various experimental settings.

Large Language Models (LLMs) have demonstrated significant advancements in various fields, notably in Role-Playing Conversational Agents (RPCAs).However, when confronted with role-specific professional inquiries, LLMsbased RPCAs tend to underperform due to their excessive emphasis on the conversational abilities of characters rather than effectively invoking and integrating relevant expert knowledge.This often results in inaccurate responses.We refer to this phenomenon as the "Knowledge Misalignment" which underscores the limitations of RPCAs in integrating expert knowledge.To mitigate this issue, we have introduced an Anchoring-Guidance Fine-Tuning (AnGFT) Framework into the RPCAs' training process.This involves initially linking the Anchoring-Based System Prompt (ASP) with the LLM's relevant expert domains through diverse prompt construction strategies and supervised fine-tuning (SFT).Following the roleplay enriched SFT, the integration of ASP enables LLMs to better associate with relevant expert knowledge, thus enhancing their response capabilities in role-specific expert domains.Moreover, we have developed four comprehensive metrics-helpfulness, thoroughness, credibility, and feasibility-to evaluate the proficiency of RPCAs in responding to professional questions.Our method was tested across four professional fields, and the experimental outcomes suggest that the proposed AnGFT Framework substantially improves the RPCAs' performance in handling role-specific professional queries, while preserving their robust role-playing abilities.

Large language models (LLMs) have significantly impacted the field of natural language processing (NLP). However, due to the limited domain specificity of the training data and the model’s constrained ability to generalize across complex biomedical data, LLMs continue to encounter challenges related to prediction bias and low generalization in biomedical named entity recognition (BioNER). In this work, we set out to improve the recognition and generalization capabilities of LLMs in BioNER through an Adversarial Selective Training (AST) method. Our method maximizes the adversarial loss to obtain the importance ranking of weights, which guides the model to selectively train to generate counterfactual examples. This strategy aims to force the model to explore the amount of information in the latent space to extract entities, thereby improving the performance of BioNER. Specifically, we conduct in-distribution experiments on five biomedical datasets and out-of-distribution experiments on two datasets. Experimental results show that our method outperforms other LLMs-based methods and significantly improves the performance of BioNER.

Inspired by the brain, Spiking Neural Network (SNN) applies temporally sparse spiking communication to gain more bio-mimetic and highly energy efficient computing. The current mainstream platforms for SNN applications are typically the combination of Host+FPGA+Chip Array, which requires an efficient host to preprocess and encode data. It’s not suitable for end-to-end tasks in edge due to its high system power consumption of host and non-negligible high latency of protocol conversion on FPGA. In addition, Convolutional Neural Network (CNN), exhibits strong feature extraction capabilities. Like the brain's visual system, a hierarchical CNN-SNN hybrid network, in which SNN can make use of CNN’s feature extraction capabilities during encoding, can achieve better performance. In this study, we design a 64Neural-Core Array and integrate it with a CNN encoder and a low-power RISC-V CPU within a System-on-Chip (SoC) to enable comprehensive end-to-end hybrid network application support. The proposed heterogeneous SoC is implemented on a Virtex UltraScale+ XCVU9P FPGA, featuring 32.8K neurons, 37.7M synapses and 578GOPS/s peak performance. It processes MNIST classification with a peak throughput of 2022 images per second at frequency of 250MHz. This design gains a balance between high throughput and recognition accuracy simultaneously.

Abstract Photovoltaic (PV) power generation is widely utilized to satisfy the increasing energy demand due to its cleanness and inexhaustibility. Accurate PV power forecasting can improve the penetration of PV power in the grid. However, it is pretty challenging to predict PV power in short‐term under precious future meteorological information absence conditions. To address this problem, this study proposes the hybrid Contrastive Learning and Temporal Convolutional Network (CL‐TCN), and this forecasting approach consists of two parts, including model training and adaptive processes of forecasting models. In the model training stage, this forecasting method firstly trains 18 TCN models for 18 time points from 9:00 a.m. to 17:30 p.m. These TCN models are trained by only using historical PV power data samples, and each model is used to predict the next half‐hour power output. The adaptive process of models means that, in a practical forecasting stage, PV power samples from historical data are firstly evaluated and scored by a CL based data scoring mechanism to search for the most similar data samples to current measured samples. Then these similar samples are further applied to training a single above‐mentioned well‐trained TCN model to improve its performance in forecasting the next half‐hour PV power. The experimental results tested at the time resolution of 30 min demonstrate that the proposed approach has superior performance in forecasting accuracy not only in smooth PV power samples but also in fluctuating PV power samples. Moreover, the proposed CL based data scoring mechanism can filter useless data samples effectively accelerating the forecasting process.

Joint entity and relation extraction (RE) construct a framework for unifying entity recognition and relationship extraction, and the approach can exploit the dependencies between the two tasks to improve the performance of the task. However, the existing tasks still have the following two problems. First, when the model extracts entity information, the boundary is blurred. Secondly, there are mostly implicit interactions between modules, that is, the interactive information is hidden inside the model, and the implicit interactions are often insufficient in the degree of interaction and lack of interpretability. To this end, this study proposes a joint entity and relation extraction model (ESEI) based on E fficient S ampling and E xplicit I nteraction. We innovatively divide negative samples into sentences based on whether they overlap with positive samples, which improves the model’s ability to extract entity word boundary information by controlling the sampling ratio. In order to increase the explicit interaction ability between the models, we introduce a heterogeneous graph neural network (GNN) into the model, which will serve as a bridge linking the entity recognition module and the relation extraction module, and enhance the interaction between the modules through information transfer. Our method substantially improves the model’s discriminative power on entity extraction tasks and enhances the interaction between relation extraction tasks and entity extraction tasks. Experiments show that the method is effective, we validate our method on four datasets, and for joint entity and relation extraction, our model improves the F1 score on multiple datasets.