Positional encoding is essential for supplementing transformer with positional information of tokens. Existing positional encoding methods demand predefined token/feature order, rendering them unsuitable for real-world data with non-sequential yet causally-related features. To address this limitation, we propose CAPE, a novel method that identifies underlying causal structure over non-sequential features as a weighted directed acyclic graph (DAG) using generalized structural equation modeling. The DAG is then embedded in hyperbolic space where its geometric structure is well-preserved using a hyperboloid model-based approach that effectively captures two important causal graph properties (causal strength & causal specificity). This step yields causality-aware positional encodings for the features, which are converted into their rotary form for integrating with transformer's self-attention mechanism. Theoretical analysis reveals that CAPE-generated rotary positional encodings possess three valuable properties for enhanced self-attention, including causal distance-induced attenuation, causal generality-induced attenuation, and robustness to positional disturbances. We evaluate CAPE over both synthetic and real-word datasets, empirically demonstrating its theoretical properties and effectiveness in enhancing transformer for data with non-sequential features. Our code is available at https://github.com/Catchxu/CAPE.

Recent speech-LLMs have shown impressive performance in tasks like transcription and translation, yet they remain limited in understanding the paralinguistic aspects of speech crucial for social and emotional intelligence. We propose CP-Bench, a benchmark for evaluating speech-LLMs on contextual paralinguistic reasoning the integration of verbal content with non-verbal cues like emotion and prosody. The benchmark includes two curated question answering (QA) datasets requiring both linguistic and empathetic understanding. We evaluate state-of-the-art speech-LLMs from both open and closed-source models and perform a comprehensive analysis across different question types. The top two models were further analyzed under temperature tuning to understand its effect on this task. Our benchmark reveals a key gap in existing evaluations and offers insights into building more context-aware and emotionally intelligent speech-capable LLMs.

Code Large Language Models (Code LLMs) have opened a new era in programming with their impressive capabilities. However, recent research has revealed critical limitations in their ability to reason about runtime behavior and understand the actual functionality of programs, which poses significant challenges for their post-training and practical deployment. Specifically, Code LLMs encounter two principal issues: (1) a lack of proficiency in reasoning about program execution behavior, as they struggle to interpret what programs actually do during runtime, and (2) the inconsistent and fragmented representation of semantic information, such as execution traces, across existing methods, which hinders their ability to generalize and reason effectively. These challenges underscore the necessity for more systematic approaches to enhance the reasoning capabilities of Code LLMs. To address these issues, we introduce a generic framework to support integrating semantic information~(e.g., execution trace) to code task-relevant prompts, and conduct a comprehensive study to explore the role of semantic information in enhancing the reasoning ability of Code LLMs accordingly. Specifically, we focus on investigating the usefulness of trace-based semantic information in boosting supervised fine-tuning~(SFT) and post-phase inference of Code LLMs. The experimental results surprisingly disagree with previous works and demonstrate that semantic information has limited usefulness for SFT and test time scaling of Code LLM.

Scientific literature question answering is a pivotal step towards new scientific discoveries. Recently, \textit{two-stage} retrieval-augmented generated large language models (RAG-LLMs) have shown impressive advancements in this domain. Such a two-stage framework, especially the second stage (reranker), is particularly essential in the scientific domain, where subtle differences in terminology may have a greatly negative impact on the final factual-oriented or knowledge-intensive answers. Despite this significant progress, the potential and limitations of these works remain unexplored. In this work, we present a Scientific Rerank-oriented RAG Benchmark (SciRerankBench), for evaluating rerankers within RAG-LLMs systems, spanning five scientific subjects. To rigorously assess the reranker performance in terms of noise resilience, relevance disambiguation, and factual consistency, we develop three types of question-context-answer (Q-C-A) pairs, i.e., Noisy Contexts (NC), Semantically Similar but Logically Irrelevant Contexts (SSLI), and Counterfactual Contexts (CC). Through systematic evaluation of 13 widely used rerankers on five families of LLMs, we provide detailed insights into their relative strengths and limitations. To the best of our knowledge, SciRerankBench is the first benchmark specifically developed to evaluate rerankers within RAG-LLMs, which provides valuable observations and guidance for their future development.

Fine-tuning massive pre-trained language models across many tasks demands adapters that are both parameter-efficient and expressive. We introduce \textbf{Kron-LoRA}, a hybrid adapter that combines Kronecker-structured factorization with low-rank LoRA compression-an integration that, to our knowledge, has not been explored in parameter-efficient fine-tuning or in matrix approximation literature. Kron-LoRA achieves up to 4$\times$ fewer parameters than standard LoRA while retaining similar expressivity. Experiments on DistilBERT, Mistral-7B, LLaMA-2-7B, and LLaMA-3-8B across eight benchmarks show that Kron-LoRA matches or exceeds LoRA baselines with modest memory savings and only a 5-8\% speed overhead. In sequential fine-tuning, it also delivers competitive cross-task transfer despite using only one-quarter of the adapter parameters. Kron-LoRA thus offers a scalable, sustainable solution for multi-task adaptation of large language models.

We present a unified and efficient pipeline for deploying multimodal large language models (MLLMs) in domain-specific settings, with a focus on dermatological visual question answering (VQA). Real-time clinical workflows require low-latency models, yet the substantial memory and computational demands of LLMs and MLLMs hinder their deployment in resource-constrained edge or cloud environments. To tackle these challenges, we introduce a compression pipeline that integrates structural pruning, supervised fine-tuning (SFT), and quantization for task specific purposes. Our approach begins with structured pruning to remove redundant parameters, reducing the model's size while preserving essential functionality. We employ a novel layer pruning criterion for domain specific applications.

Background and Aims: Large language models (LLMs) have shown remarkable generalization and transfer capabilities by learning from vast corpora of text and web data. Their semantic representations allow cross-task knowledge transfer and reasoning, offering promising opportunities for data-scarce and heterogeneous domains such as clinical medicine. Yet, in diagnostic tasks like sarcopenia, major challenges remain: interpretability, transparency, and deployment efficiency. Traditional machine learning (TML) models provide stable performance and feature-level attribution, ensuring traceable and auditable decision logic, but lack semantic breadth. Conversely, LLMs enable flexible inference but often function as opaque predictors. Existing integration strategies remain shallow, rarely embedding the structured reasoning of TML into LLM inference. Methods: Using sarcopenia diagnosis as a case study, SHapley Additive exPlanations (SHAP) were extracted from a baseline XGBoost model and transformed into structured, LLM-compatible representations. An actor-critic reinforcement learning (RL) strategy guided the LLM to reason over these SHAP-based inputs, producing calibrated rationales and refined decision rules. The distilled reasoning was consolidated into a structured knowledge repository and deployed via retrieval-augmented generation (RAG) for case-based inference. Results: (Omitted here.) Conclusion: By coupling SHAP-derived statistical evidence with reinforcement-trained LLM reasoning, CANDLE mitigates the interpretability-performance trade-off, enhances predictive accuracy, and preserves high decision consistency. The framework offers a scalable approach to knowledge assetization of TML models, enabling interpretable, reproducible, and clinically aligned decision support in sarcopenia and potentially broader medical domains.

Recent research has focused on applying speech large language model (SLLM) to improve speech emotion recognition (SER). However, the inherently high frame rate in speech modality severely limits the signal processing and understanding capabilities of SLLM. For example, a SLLM with a 4K context window can only process 80 seconds of audio at 50Hz feature sampling rate before reaching its capacity limit. Input token compression methods used in SLLM overlook the continuity and inertia of emotions across multiple conversation turns. This paper proposes a Dynamic Parameter Memory (DPM) mechanism with contextual semantics and sentence-level emotion encoding, enabling processing of unlimited-length audio with limited context windows in SLLM. Specifically, DPM progressively encodes sentence-level information and emotions into a temporary LoRA module during inference to effectively "memorize" the contextual information. We trained an emotion SLLM as a backbone and incorporated our DPM into inference for emotion recognition in conversation (ERC). Experimental results on the IEMOCAP and MELD datasets show that DPM significantly improves the emotion recognition capabilities of SLLM when processing long audio sequences, achieving state-of-the-art performance.

Parameter-Efficient Fine-Tuning (PEFT) methods, such as LoRA, significantly reduce the number of trainable parameters by introducing low-rank decomposition matrices. However, existing methods perform extensive matrix multiplications in domain specialization tasks, resulting in computational inefficiency and sub-optimal fine-tuning performance. Hence, we propose LoSiA(Low-Resources Subnet Integration Adaptation), an innovative method that dynamically localizes and optimizes critical parameters during the training process. Specifically, it identifies a sub-network using gradient sparsity analysis and optimizes it as the trainable target. This design enables effective high-rank adaptation by updating only the sub-network parameters, reducing the additional matrix multiplication. We also present LoSiA-Pro, a faster implementation of LoSiA, which reduces the training latency by about $27\%$ compared to LoRA. Extensive evaluations show that our method achieves minimal performance drop compared to full fine-tuning, while requiring the least training time across domain specialization and common-sense reasoning tasks. Further analysis shows that LoSiA also reduces forgetting during continued training. The source code is available at https://github.com/KlozeWang/LoSiA.

Recent advances in deep learning have led to increasingly complex models with deeper layers and more parameters, reducing interpretability and making their decisions harder to understand. While many methods explain black-box reasoning, most lack effective interventions or only operate at sample-level without modifying the model itself. T o address this, we propose the Concept Bottleneck Model for Enhancing Human-Neural Network Mutual Understanding (CBM-HNMU). CBM-HNMU leverages the Concept Bottleneck Model (CBM) as an interpretable framework to approximate black-box reasoning and communicate conceptual understanding. Detrimental concepts are automatically identified and refined (removed/replaced) based on global gradient contributions. The modified CBM then distills corrected knowledge back into the black-box model, enhancing both interpretability and accuracy. W e evaluate CBM-HNMU on various CNN and transformer-based models across Flower-102, CIF AR-10, CIF AR-100, FGVC-Aircraft, and CUB-200, achieving a maximum accuracy improvement of 2.64% and a maximum increase in average accuracy across 1.03%.