Spectral analysis provides crucial clues for the elucidation of unknown materials. Among various techniques, infrared spectroscopy (IR) plays an important role in laboratory settings due to its high accessibility and low cost. However, existing approaches often fail to reflect expert analytical processes and lack flexibility in incorporating diverse types of chemical knowledge, which is essential in real-world analytical scenarios. In this paper, we propose IR-Agent, a novel multi-agent framework for molecular structure elucidation from IR spectra. The framework is designed to emulate expert-driven IR analysis procedures and is inherently extensible. Each agent specializes in a specific aspect of IR interpretation, and their complementary roles enable integrated reasoning, thereby improving the overall accuracy of structure elucidation. Through extensive experiments, we demonstrate that IR-Agent not only improves baseline performance on experimental IR spectra but also shows strong adaptability to various forms of chemical information.

Transformer-based language models (LMs) can perform a wide range of tasks, and mechanistic interpretability (MI) aims to reverse engineer the components responsible for task completion to understand their behavior. Previous MI research has focused on linguistic tasks such as Indirect Object Identification (IOI). In this paper, we investigate the ability of GPT-2 small to handle binary truth values by analyzing its behavior with syllogistic prompts, e.g., "Statement A is true. Statement B matches statement A. Statement B is", which requires more complex logical reasoning compared to IOI. Through our analysis of several syllogism tasks of varying difficulty, we identify multiple circuits that mechanistically explain GPT-2's logical-reasoning capabilities and uncover binary mechanisms that facilitate task completion, including the ability to produce a negated token not present in the input prompt through negative heads. Our evaluation using a faithfulness metric shows that a circuit comprising five attention heads achieves over 90% of the original model's performance. By relating our findings to IOI analysis, we provide new insights into the roles of specific attention heads and MLPs in LMs. These insights contribute to a broader understanding of model reasoning and support future research in mechanistic interpretability.

Instruction tuning is vital for aligning large language models (LLMs) with human intent, but current methods typically rely on costly human-annotated seed data or powerful external teacher models. While instruction back-translation techniques reduce this dependency, they remain fundamentally tethered to an initial seed set, which limits full automation, introduces biases, and can lead to inefficient use of unlabeled corpora. In this paper, we propose Cycle-Instruct, a novel framework that achieves fully seed-free instruction tuning. Inspired by cycle consistency, Cycle-Instruct employs a dual self-training loop where two models-an answer generator and a question generator-are bootstrapped solely from raw, unlabeled text. These models mutually supervise each other by reconstructing original text segments from their counterpart's generated pseudo-labels, effectively learning from the intrinsic structure of the data without any human-provided seeds. We demonstrate Cycle-Instruct's efficacy across four diverse data tracks, including general instruction-following, domain-specific tasks, dialogue logs, and plain text. Our extensive experiments show that Cycle-Instruct not only outperforms seed-driven back-translation baselines but also achieves performance comparable to strongly supervised methods.

Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of general-domain tasks. However, their effectiveness in specialized fields, such as construction, remains underexplored. In this paper, we introduce CEQuest, a novel benchmark dataset specifically designed to evaluate the performance of LLMs in answering construction-related questions, particularly in the areas of construction drawing interpretation and estimation. We conduct comprehensive experiments using five state-of-the-art LLMs, including Gemma 3, Phi4, LLaVA, Llama 3.3, and GPT-4.1, and evaluate their performance in terms of accuracy, execution time, and model size. Our experimental results demonstrate that current LLMs exhibit considerable room for improvement, highlighting the importance of integrating domain-specific knowledge into these models. To facilitate further research, we will open-source the proposed CEQuest dataset, aiming to foster the development of specialized large language models (LLMs) tailored to the construction domain.

This paper describes our approach to automated program repair. We combine various techniques from the literature to achieve this. Our experiments show that our approach performs better than other techniques on standard benchmarks. However, on closer inspection, none of these techniques work on realistic defects that we see in industry. We find that augmenting code with formal specifications enables LLMs to generate higher-quality unit tests, especially for complex production code with improved coverage of edge cases and exception handling. However, specifications add little value for well-understood errors (e.g., null pointer, index out of bounds), but are beneficial for logic and string manipulation errors. Despite encouraging benchmark results, real-world adoption is limited since passing tests do not guarantee correct patches. Current challenges include insufficient expressiveness of the JML specification language, necessitating advanced verification tools and richer predicates. Our ongoing work is exploring contract automata, programming by example, and testcase repair, with a focus on integrating human feedback and measuring productivity gains - highlighting the gap between academic benchmarks and practical industry needs

Large language models (LLMs) have demonstrated tremendous potential in game playing, while little attention has been paid to their ethical implications in those contexts. This work investigates and analyses the ethical considerations of applying LLMs in game playing, using Werewolf, also known as Mafia, as a case study. Gender bias, which affects game fairness and player experience, has been observed from the behaviour of LLMs. Some roles, such as the Guard and Werewolf, are more sensitive than others to gender information, presented as a higher degree of behavioural change. We further examine scenarios in which gender information is implicitly conveyed through names, revealing that LLMs still exhibit discriminatory tendencies even in the absence of explicit gender labels. This research showcases the importance of developing fair and ethical LLMs. Beyond our research findings, we discuss the challenges and opportunities that lie ahead in this field, emphasising the need for diving deeper into the ethical implications of LLMs in gaming and other interactive domains.

Time series (TS) data are ubiquitous across various application areas, rendering time series forecasting (TSF) a fundamental task. With the astounding advances in large language models (LLMs), a variety of methods have been developed to adapt LLMs for time series forecasting. Despite unlocking the potential of LLMs in comprehending TS data, existing methods are inherently constrained by their shallow integration of TS information, wherein LLMs typically access TS representations at shallow layers, primarily at the input layer. This causes the influence of TS representations to progressively fade in deeper layers and eventually leads to ineffective adaptation between textual embeddings and TS representations. In this paper, we propose the Multi-layer Steerable Embedding Fusion (MSEF), a novel framework that enables LLMs to directly access time series patterns at all depths, thereby mitigating the progressive loss of TS information in deeper layers. Specifically, MSEF leverages off-the-shelf time series foundation models to extract semantically rich embeddings, which are fused with intermediate text representations across LLM layers via layer-specific steering vectors. These steering vectors are designed to continuously optimize the alignment between time series and textual modalities and facilitate a layer-specific adaptation mechanism that ensures efficient few-shot learning capabilities. Experimental results on seven benchmarks demonstrate significant performance improvements by MSEF compared with baselines, with an average reduction of 31.8% in terms of MSE. The code is available at https://github.com/One1sAll/MSEF.

Electronic health records (EHRs) are rich clinical data sources but complex repositories of patient data, spanning structured elements (demographics, vitals, lab results, codes), unstructured clinical notes and other modalities of data. Harnessing this heterogeneity is critical for improving patient outcomes. Recent advances in large language models (LLMs) have enabled foundation models that can learn from multiple data modalities and support clinical tasks. However, most current approaches simply serialize numeric EHR data into text, which risks losing temporal and quantitative detail. We introduce Generative Deep Patient (GDP), a multimodal foundation model that natively encodes structured EHR time-series via a CNN-Transformer encoder and fuses it with unstructured EHRs through cross-modal attention into a LLaMA-based decoder. GDP is trained in two stages: (1) generative pretraining, where it learns to produce clinical narratives from raw patient timelines while also performing masked feature prediction (MFP) and next time-step prediction (NTP) to capture temporal dynamics; and (2) multi-task fine-tuning for clinically meaningful predictions (e.g., heart failure, type 2 diabetes, 30-day readmission). In clinical prediction, GDP demonstrated superior performance on MIMIC-IV: heart failure AUROC = 0.923, type 2 diabetes AUROC = 0.817, and 30-day readmission AUROC = 0.627. For narrative generation, GDP achieved ROUGE-L = 0.135 and BERTScore-F1 = 0.545. In a blinded human evaluation, GDP-Instruct scored highest on faithfulness, fluency, and overall clinical utility, suggesting reduced hospital documentation workload without sacrificing accuracy. Our results demonstrate that a single multimodal foundation model can both predict clinically actionable events and generate high-quality clinical narratives. Furthermore, GDP's flexible architecture can be extended to additional modalities.

Large language models (LLMs) are increasingly deployed in politically sensitive settings, raising concerns about their potential to encode, amplify, or be steered toward specific ideologies. We investigate how adopting synthetic personas influences ideological expression in LLMs across seven models (7B-70B+ parameters) from multiple families, using the Political Compass Test as a standardized probe. Our analysis reveals four consistent patterns: (i) larger models display broader and more polarized implicit ideological coverage; (ii) susceptibility to explicit ideological cues grows with scale; (iii) models respond more strongly to right-authoritarian than to left-libertarian priming; and (iv) thematic content in persona descriptions induces systematic and predictable ideological shifts, which amplify with size. These findings indicate that both scale and persona content shape LLM political behavior. As such systems enter decision-making, educational, and policy contexts, their latent ideological malleability demands attention to safeguard fairness, transparency, and safety.

In this chapter, we argue for the benefits of understanding multiword expressions from the perspective of usage-based, construction grammar approaches. We begin with a historical overview of how construction grammar was developed in order to account for idiomatic expressions using the same grammatical machinery as the non-idiomatic structures of language. We cover a comprehensive description of constructions, which are pairings of meaning with form of any size (morpheme, word, phrase), as well as how constructional approaches treat the acquisition and generalization of constructions. We describe a successful case study leveraging constructional templates for representing multiword expressions in English PropBank. Because constructions can be at any level or unit of form, we then illustrate the benefit of a constructional representation of multi-meaningful morphosyntactic unit constructions in Arapaho, a highly polysynthetic and agglutinating language. We include a second case study leveraging constructional templates for representing these multi-morphemic expressions in Uniform Meaning Representation. Finally, we demonstrate the similarities and differences between a usage-based explanation of a speaker learning a novel multiword expression, such as "dancing with deer," and that of a large language model. We present experiments showing that both models and speakers can generalize the meaning of novel multiword expressions based on a single exposure of usage. However, only speakers can reason over the combination of two such expressions, as this requires comparison of the novel forms to a speaker's lifetime of stored constructional exemplars, which are rich with cross-modal details.