Direct Alignment Algorithms (DAAs) such as Direct Preference Optimization (DPO) have emerged as alternatives to the standard Reinforcement Learning from Human Feedback (RLHF) for aligning large language models (LLMs) with human values. However, these methods are more susceptible to over-optimization, in which the model drifts away from the reference policy, leading to degraded performance as training progresses. This paper proposes a novel importance-sampling approach to mitigate the over-optimization problem of offline DAAs. This approach, called (IS-DAAs), multiplies the DAA objective with an importance ratio that accounts for the reference policy distribution. IS-DAAs additionally avoid the high variance issue associated with importance sampling by clipping the importance ratio to a maximum value. Our extensive experiments demonstrate that IS-DAAs can effectively mitigate over-optimization, especially under low regularization strength, and achieve better performance than other methods designed to address this problem. Our implementations are provided publicly at this link.

Communication system formulation is critical for advancing 6G and future wireless technologies, yet it remains a complex, expertise-intensive task. While Large Language Models (LLMs) offer potential, existing general-purpose models often lack the specialized domain knowledge, nuanced reasoning capabilities, and access to high-quality, domain-specific training data required for adapting a general LLM into an LLM specially for communication system formulation. To bridge this gap, we introduce DeepForm, the first reasoning LLM specially for automated communication system formulation. We propose the world-first large-scale, open-source dataset meticulously curated for this domain called Communication System Formulation Reasoning Corpus (CSFRC). Our framework employs a two-stage training strategy: first, Supervised Fine-Tuning (SFT) with Chain-of-Thought (CoT) data to distill domain knowledge; second, a novel rule-based Reinforcement Learning (RL) algorithm, C-ReMax based on ReMax, to cultivate advanced modeling capabilities and elicit sophisticated reasoning patterns like self-correction and verification. Extensive experiments demonstrate that our model achieves state-of-the-art performance, significantly outperforming larger proprietary LLMs on diverse senerios. We will release related resources to foster further research in this area after the paper is accepted.

Large Language Models (LLMs) have shown remarkable capabilities in text and multimodal processing, yet they fundamentally lack physical awareness--understanding of real-world physical phenomena. In this work, we present ACORN, a framework that teaches LLMs physical awareness through sound, focusing on fundamental physical phenomena like the Doppler effect, multipath effect, and spatial relationships. To overcome data scarcity, ACORN introduce a physics-based simulator combining real-world sound sources with controlled physical channels to generate diverse training data. Using this simulator, we build AQA-PHY, a comprehensive Audio Question-Answer dataset, and propose an audio encoder that processes both magnitude and phase information. By connecting our audio encoder to state-of-the-art LLMs, we demonstrate reasonable results in both simulated and real-world tasks, such as line-of-sight detection, Doppler effect estimation, and Direction-of-Arrival estimation, paving the way for enabling LLMs to understand physical world.

Training Large Language Models (LLMs) is costly in terms of energy, hardware, and annotated data, often resulting in a positionality rooted in predominant cultures and values (Santy et al., 2023). Domain adaptation has emerged as a promising strategy to better align models with diverse cultural and value contexts (Hershcovich et al., 2022), but its computational cost remains a significant barrier, particularly for research groups lacking access to large-scale infrastructure. In this paper, we evaluate how the use of different numerical precision formats and data parallelization strategies impacts both training speed (as a proxy to energy and hardware consumption) and model accuracy, with the goal of facilitating domain adaptation in low-resource environments. Our findings are relevant to any setting where energy efficiency, accessibility, or limited hardware availability are key concerns.

Recent advances toward foundation models for routing problems have shown great potential of a unified deep model for various VRP variants. However, they overlook the complex real-world customer distributions. In this work, we advance the Multi-Task VRP (MTVRP) setting to the more realistic yet challenging Multi-Task Multi-Distribution VRP (MTMDVRP) setting, and introduce SHIELD, a novel model that leverages both sparsity and hierarchy principles. Building on a deeper decoder architecture, we first incorporate the Mixture-of-Depths (MoD) technique to enforce sparsity. This improves both efficiency and generalization by allowing the model to dynamically select nodes to use or skip each decoder layer, providing the needed capacity to adaptively allocate computation for learning the task/distribution specific and shared representations. We also develop a context-based clustering layer that exploits the presence of hierarchical structures in the problems to produce better local representations. These two designs inductively bias the network to identify key features that are common across tasks and distributions, leading to significantly improved generalization on unseen ones. Our empirical results demonstrate the superiority of our approach over existing methods on 9 real-world maps with 16 VRP variants each.

Having a unified, coherent taxonomy is essential for effective knowledge representation in domain-specific applications as diverse terminologies need to be mapped to underlying concepts. Traditional manual approaches to taxonomy alignment rely on expert review of concept pairs, but this becomes prohibitively expensive and time-consuming at scale, while subjective interpretations often lead to expert disagreements. Existing automated methods for taxonomy alignment have shown promise but face limitations in handling nuanced semantic relationships and maintaining consistency across different domains. These approaches often struggle with context-dependent concept mappings and lack transparent reasoning processes. We propose a novel framework that combines large language models (LLMs) with expert calibration and iterative prompt optimization to automate taxonomy alignment. Our method integrates expert-labeled examples, multi-stage prompt engineering, and human validation to guide LLMs in generating both taxonomy linkages and supporting rationales. In evaluating our framework on a domain-specific mapping task of concept essentiality, we achieved an F1-score of 0.97, substantially exceeding the human benchmark of 0.68. These results demonstrate the effectiveness of our approach in scaling taxonomy alignment while maintaining high-quality mappings and preserving expert oversight for ambiguous cases.

Ensuring safe and appropriate responses from vision-language models (VLMs) remains a critical challenge, particularly in high-risk or ambiguous scenarios. We introduce SafeCoT, a lightweight, interpretable framework that leverages rule-based chain-of-thought (CoT) supervision to improve refusal behavior in VLMs. Unlike prior methods that rely on large-scale safety annotations or complex modeling, SafeCoT uses minimal supervision to help models reason about safety risks and make context-aware refusals. Experiments across multiple benchmarks show that SafeCoT significantly reduces overrefusal and enhances generalization, even with limited training data. Our approach offers a scalable solution for aligning VLMs with safety-critical objectives.

While Large Language Models (LLMs) support long contexts, they struggle with performance degradation within the context window. Current solutions incur prohibitive training costs, leaving statistical behaviors and cost-effective approaches underexplored. From the decoding perspective, we identify the Posterior Salience Attenuation (PSA) phenomenon, where the salience ratio correlates with long-text performance degradation. Notably, despite the attenuation, gold tokens still occupy high-ranking positions in the decoding space. Motivated by it, we propose the training-free Positional Contrastive Decoding (PCD) that contrasts the logits derived from long-aware attention with those from designed local-aware attention, enabling the model to focus on the gains introduced by large-scale short-to-long training. Through the analysis of long-term decay simulation, we demonstrate that PCD effectively alleviates attention score degradation. Experimental results show that PCD achieves state-of-the-art performance on long-context benchmarks.

Despite their growing adoption across domains, large language model (LLM)-powered agents face significant security risks from backdoor attacks during training and fine-tuning. These compromised agents can subsequently be manipulated to execute malicious operations when presented with specific triggers in their inputs or environments. To address this pressing risk, we present ReAgent, a novel defense against a range of backdoor attacks on LLM-based agents. Intuitively, backdoor attacks often result in inconsistencies among the user's instruction, the agent's planning, and its execution. Drawing on this insight, ReAgent employs a two-level approach to detect potential backdoors. At the execution level, ReAgent verifies consistency between the agent's thoughts and actions; at the planning level, ReAgent leverages the agent's capability to reconstruct the instruction based on its thought trajectory, checking for consistency between the reconstructed instruction and the user's instruction. Extensive evaluation demonstrates ReAgent's effectiveness against various backdoor attacks across tasks. For instance, ReAgent reduces the attack success rate by up to 90\% in database operation tasks, outperforming existing defenses by large margins. This work reveals the potential of utilizing compromised agents themselves to mitigate backdoor risks.

The rapid expansion of English technical terminology presents a significant challenge to traditional expert-based standardization, particularly in rapidly developing areas such as artificial intelligence and quantum computing. Manual approaches face difficulties in maintaining consistent multilingual terminology. To address this, we introduce LLM-BT, a back-translation framework powered by large language models (LLMs) designed to automate terminology verification and standardization through cross-lingual semantic alignment. Our key contributions include: (1) term-level consistency validation: by performing English -> intermediate language -> English back-translation, LLM-BT achieves high term consistency across different models (such as GPT-4, DeepSeek, and Grok). Case studies demonstrate over 90 percent of terms are preserved either exactly or semantically; (2) multi-path verification workflow: we develop a novel pipeline described as Retrieve -> Generate -> Verify -> Optimize, which supports both serial paths (e.g., English -> Simplified Chinese -> Traditional Chinese -> English) and parallel paths (e.g., English -> Chinese / Portuguese -> English). BLEU scores and term-level accuracy indicate strong cross-lingual robustness, with BLEU scores exceeding 0.45 and Portuguese term accuracy reaching 100 percent; (3) back-translation as semantic embedding: we reinterpret back-translation as a form of dynamic semantic embedding that uncovers latent trajectories of meaning. In contrast to static embeddings, LLM-BT offers transparent, path-based embeddings shaped by the evolution of the models. This reframing positions back-translation as an active mechanism for multilingual terminology standardization, fostering collaboration between machines and humans - machines preserve semantic integrity, while humans provide cultural interpretation.