We conduct experiments on the impact of increasing inference-time compute in reasoning models (specifically OpenAI o1-preview and o1-mini) on their robustness to adversarial attacks. We find that across a variety of attacks, increased inference-time compute leads to improved robustness. In many cases (with important exceptions), the fraction of model samples where the attack succeeds tends to zero as the amount of test-time compute grows. We perform no adversarial training for the tasks we study, and we increase inference-time compute by simply allowing the models to spend more compute on reasoning, independently of the form of attack. Our results suggest that inference-time compute has the potential to improve adversarial robustness for Large Language Models. We also explore new attacks directed at reasoning models, as well as settings where inference-time compute does not improve reliability, and speculate on the reasons for these as well as ways to address them.

Real-world open-domain questions can be complicated, particularly when answering them involves information from multiple information sources. LLMs have demonstrated impressive performance in decomposing complex tasks into simpler steps, and previous work has used it for better retrieval in support of complex questions. However, LLM's decomposition of questions is unaware of what data is available and how data is organized, often leading to a sub-optimal retrieval performance. Recent effort in agentic RAG proposes to perform retrieval in an iterative fashion, where a followup query is derived as an action based on previous rounds of retrieval. While this provides one way of interacting with the data collection, agentic RAG's exploration of data is inefficient because successive queries depend on previous results rather than being guided by the organization of available data in the collection. To address this problem, we propose an LLM-based retrieval method -- ARM, that aims to better align the question with the organization of the data collection by exploring relationships among data objects beyond matching the utterance of the query, thus leading to a retrieve-all-at-once solution for complex queries. We evaluated ARM on two datasets, Bird and OTT-QA. On Bird, it outperforms standard RAG with query decomposition by up to 5.2 pt in execution accuracy and agentic RAG (ReAct) by up to 15.9 pt. On OTT-QA, it achieves up to 5.5 pt and 19.3 pt higher F1 match scores compared to these approaches.

We present an interactive and explainable automated coaching assistant called CueTip for a variant of pool/billiards. CueTip's novelty lies in its combination of three features: a natural-language interface, an ability to perform contextual, physics-aware reasoning, and that its explanations are rooted in a set of predetermined guidelines developed by domain experts. We instrument a physics simulator so that it generates event traces in natural language alongside traditional state traces. Event traces lend themselves to interpretation by language models, which serve as the interface to our assistant. We design and train a neural adaptor that decouples tactical choices made by CueTip from its interactivity and explainability allowing it to be reconfigured to mimic any pool playing agent. Our experiments show that CueTip enables contextual query-based assistance and explanations while maintaining the strength of the agent in terms of win rate (improving it in some situations). The explanations generated by CueTip are physically-aware and grounded in the expert rules and are therefore more reliable.

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external knowledge retrieved from a knowledge base. However, its effectiveness is fundamentally constrained by the reliability of both the retriever and the knowledge base. In real-world scenarios, imperfections in these components often lead to the retrieval of noisy, irrelevant, or misleading counterfactual information, ultimately undermining the trustworthiness of RAG systems. To address this challenge, we propose Robust Fine-Tuning (RbFT), a method designed to enhance the resilience of LLMs against retrieval defects through two targeted fine-tuning tasks. Experimental results demonstrate that RbFT significantly improves the robustness of RAG systems across diverse retrieval conditions, surpassing existing methods while maintaining high inference efficiency and compatibility with other robustness techniques.

Transformer-based models have demonstrated remarkable ability in in-context learning (ICL), where they can adapt to unseen tasks from a prompt with a few examples, without requiring parameter updates. Recent research has provided insight into how linear Transformers can perform ICL by implementing gradient descent estimators. In particular, it has been shown that the optimal linear self-attention (LSA) mechanism can implement one step of gradient descent with respect to a linear least-squares objective when trained on random linear regression tasks. However, the theoretical understanding of ICL for nonlinear function classes remains limited. In this work, we address this gap by first showing that LSA is inherently restricted to solving linear least-squares objectives and thus, the solutions in prior works cannot readily extend to nonlinear ICL tasks. To overcome this limitation, drawing inspiration from modern architectures, we study a mechanism that combines LSA with GLU-like feed-forward layers and show that this allows the model to perform one step of gradient descent on a polynomial kernel regression. Further, we characterize the scaling behavior of the resulting Transformer model, highlighting the necessary model size to effectively handle quadratic ICL tasks. Our findings highlight the distinct roles of attention and feed-forward layers in nonlinear ICL and identify key challenges when extending ICL to nonlinear function classes.

Structured embedding transformations offer a promising approach for enhancing the efficiency and coherence of language model inference. The introduction of Structural Embedding Projection (SEP) provides a mechanism for refining token representations through projection matrices that integrate hierarchical and relational dependencies. The mathematical formulation of SEP enables embedding spaces to capture structured contextual relationships, thereby improving semantic fidelity without significantly increasing computational overhead. Experimental evaluations conducted on a range of linguistic datasets revealed that SEP contributed to reductions in perplexity and enhanced contextual coherence, demonstrating its potential to refine language model outputs. Computational efficiency assessments highlighted variations across different datasets, suggesting that the integration of structured embeddings introduced dataset-dependent trade-offs between inference speed and representational richness. The qualitative analysis of generated responses indicated that SEP enhanced narrative consistency and topic alignment, leading to improved fluency in multi-sentence text generation. The modifications to embedding layers required precise optimization to ensure stable training dynamics, as the introduction of structured transformations altered the traditional representation-learning process. The architectural adjustments necessary for SEP implementation influenced inference latency and memory consumption, requiring a balance between efficiency gains and additional processing demands. The impact of SEP on lexical diversity suggested that embedding modifications influenced the model's vocabulary usage, reflecting a more context-aware selection of generated tokens.

Social telehealth has revolutionized healthcare by enabling patients to share symptoms and receive medical consultations remotely. Users frequently post symptoms on social media and online health platforms, generating a vast repository of medical data that can be leveraged for disease classification and symptom severity assessment. Large language models (LLMs), such as LLAMA3, GPT-3.5 Turbo, and BERT, process complex medical data to enhance disease classification. This study explores three Arabic medical text preprocessing techniques: text summarization, text refinement, and Named Entity Recognition (NER). Evaluating CAMeL-BERT, AraBERT, and Asafaya-BERT with LoRA, the best performance was achieved using CAMeL-BERT with NER-augmented text (83% type classification, 69% severity assessment). Non-fine-tuned models performed poorly (13%-20% type classification, 40%-49% severity assessment). Integrating LLMs into social telehealth systems enhances diagnostic accuracy and treatment outcomes.

The increasing size and complexity of pre-trained language models have demonstrated superior performance in many applications, but they usually require large training datasets to be adequately trained. Insufficient training sets could unexpectedly make the model overfit and fail to cope with complex tasks. Large language models (LLMs) trained on extensive corpora have prominent text generation capabilities, which improve the quality and quantity of data and play a crucial role in data augmentation. Specifically, distinctive prompt templates are given in personalised tasks to guide LLMs in generating the required content. Recent promising retrieval-based techniques further improve the expressive performance of LLMs in data augmentation by introducing external knowledge to enable them to produce more grounded-truth data. This survey provides an in-depth analysis of data augmentation in LLMs, classifying the techniques into Simple Augmentation, Prompt-based Augmentation, Retrieval-based Augmentation and Hybrid Augmentation. We summarise the post-processing approaches in data augmentation, which contributes significantly to refining the augmented data and enabling the model to filter out unfaithful content. Then, we provide the common tasks and evaluation metrics. Finally, we introduce existing challenges and future opportunities that could bring further improvement to data augmentation.

While systems designed for solving planning tasks vastly outperform Large Language Models (LLMs) in this domain, they usually discard the rich semantic information embedded within task descriptions. In contrast, LLMs possess parametrised knowledge across a wide range of topics, enabling them to leverage the natural language descriptions of planning tasks in their solutions. However, current research in this direction faces challenges in generating correct and executable plans. Furthermore, these approaches depend on the LLM to output solutions in an intermediate language, which must be translated into the representation language of the planning task. We introduce a novel planning method, which leverages the parametrised knowledge of LLMs by using their output as a heuristic for Hill-Climbing Search. This approach is further enhanced by prompting the LLM to generate a solution estimate to guide the search. Our method outperforms the task success rate of similar systems within a common household environment by 22 percentage points, with consistently executable plans. All actions are encoded in their original representation, demonstrating that strong results can be achieved without an intermediate language, thus eliminating the need for a translation step.

The rapid advancement of large language models (LLMs) has made detecting AI-generated text an increasingly critical challenge. Traditional methods often fail to capture the nuanced semantic differences between human and machine-generated content. We therefore propose a novel approach based on semantic similarity analysis, leveraging a multi-layered architecture that combines a pre-trained DeBERTa-v3-large model, Bi-directional LSTMs, and linear attention pooling to capture both local and global semantic patterns. To enhance performance, we employ advanced input and output augmentation techniques such as sector-level context integration and wide output configurations. These techniques enable the model to learn more discriminative features and generalize across diverse domains. Experimental results show that this approach works better than traditional methods, proving its usefulness for AI-generated text detection and other text comparison tasks.