We formalize coherence --a requirement that erroneous predictions, within a slice, should be wrong for the same reason --as a key property that any slice discovery method should satisfy.

Large Language Models (LLMs) are rapidly being adopted in conservation to address the biodiversity crisis, yet their reliability for species evaluation is uncertain. This study systematically validates five leading models on 21,955 species across four core IUCN Red List assessment components: taxonomy, conservation status, distribution, and threats. A critical paradox was revealed: models excelled at taxonomic classification (94.9%) but consistently failed at conservation reasoning (27.2% for status assessment). This knowledge-reasoning gap, evident across all models, suggests inherent architectural constraints, not just data limitations. Furthermore, models exhibited systematic biases favoring charismatic vertebrates, potentially amplifying existing conservation inequities. These findings delineate clear boundaries for responsible LLM deployment: they are powerful tools for information retrieval but require human oversight for judgment-based decisions. A hybrid approach is recommended, where LLMs augment expert capacity while human experts retain sole authority over risk assessment and policy.

Slot and intent detection (SID) is a classic natural language understanding task. Despite this, research has only more recently begun focusing on SID for dialectal and colloquial varieties. Many approaches for low-resource scenarios have not yet been applied to dialectal SID data, or compared to each other on the same datasets. We participate in the VarDial 2025 shared task on slot and intent detection in Norwegian varieties, and compare multiple set-ups: varying the training data (English, Norwegian, or dialectal Norwegian), injecting character-level noise, training on auxiliary tasks, and applying Layer Swapping, a technique in which layers of models fine-tuned on different datasets are assembled into a model. We find noise injection to be beneficial while the effects of auxiliary tasks are mixed. Though some experimentation was required to successfully assemble a model from layers, it worked surprisingly well; a combination of models trained on English and small amounts of dialectal data produced the most robust slot predictions. Our best models achieve 97.6% intent accuracy and 85.6% slot F1 in the shared task.

In-Context Learning (ICL) is a technique by which language models make predictions based on examples provided in their input context. Previously, their context window size imposed a limit on the number of examples that can be shown, making example selection techniques crucial for identifying the maximally effective set of examples. However, the recent advent of Long Context Language Models (LCLMs) has significantly increased the number of examples that can be included in context, raising an important question of whether ICL performance in a many-shot regime is still sensitive to the method of sample selection. To answer this, we revisit these approaches in the context of LCLMs through extensive experiments on 18 datasets spanning 4 tasks. Surprisingly, we observe that sophisticated example selection techniques do not yield significant improvements over a simple random sample selection method. Instead, we find that the advent of LCLMs has fundamentally shifted the challenge of ICL from that of selecting the most effective examples to that of collecting sufficient examples to fill the context window. Specifically, in certain datasets, including all available examples does not fully utilize the context window; however, by augmenting the examples in context with a simple data augmentation approach, we substantially improve ICL performance by 5%.

One of that obtaining explanations of idiomatic expressions the main areas of interest for the proponents of in the learner's first language removes many technology-assisted language learning is vocabulary of the barriers to understanding introduced by traditional expansion, where recent studies have demonstrated definition generation systems. We choose a significant impact in student engagement to focus on idiomatic expressions as they are an and increased vocabulary knowledge (Fisher, 2016; important element of language learning that is particularly Guaqueta and Castro-Gárces, 2018; Tao Hao and challenging for learners and automated Ardasheva, 2021). To support the development systems alike. Consider the utterance, he and I of these technologies, considerable work has been don't see eye to eye on a variety of topics. The idiomatic devoted to the study of automated definition generation expression contained within this sentence (Ni and Wang, 2017; Gadetsky et al., 2018; is not composed of particularly challenging words, Ishiwatari et al., 2019; Bevilacqua et al., 2020).

Large language models (LLMs) hold promise for addressing healthcare challenges but often generate hallucinations due to limited integration of medical knowledge. Incorporating external medical knowledge is therefore critical, especially considering the breadth and complexity of medical content, which necessitates effective multi-source knowledge acquisition. We address this challenge by framing it as a source planning problem, where the task is to formulate context-appropriate queries tailored to the attributes of diverse knowledge sources. Existing approaches either overlook source planning or fail to achieve it effectively due to misalignment between the model's expectation of the sources and their actual content. To bridge this gap, we present MedOmniKB, a comprehensive repository comprising multigenre and multi-structured medical knowledge sources. Leveraging these sources, we propose the Source Planning Optimisation (SPO) method, which enhances multi-source utilisation through explicit planning optimisation. Our approach involves enabling an expert model to explore and evaluate potential plans while training a smaller model to learn source alignment using positive and negative planning samples. Experimental results demonstrate that our method substantially improves multi-source planning performance, enabling the optimised small model to achieve state-of-the-art results in leveraging diverse medical knowledge sources.

Large language models (LLMs) demonstrate exceptional capabilities, yet still face the hallucination issue. Typical text generation approaches adopt an auto-regressive generation without deliberate reasoning, which often results in untrustworthy and factually inaccurate responses. In this paper, we propose HaluSearch, a novel framework that incorporates tree search-based algorithms (e.g., MCTS) to enable an explicit slow thinking generation process for mitigating hallucinations of LLMs during inference. Specifically, HaluSearch frames text generation as a step-by-step reasoning process, using a self-evaluation reward model to score each generation step and guide the tree search towards the most reliable generation pathway for fully exploiting the internal knowledge of LLMs. To balance efficiency and quality, we introduce a hierarchical thinking system switch mechanism inspired by the dual process theory in cognitive science, which dynamically alternates between fast and slow thinking modes at both the instance and step levels, adapting to the complexity of questions and reasoning states. We conduct extensive experiments on both English and Chinese datasets and the results show that our approach significantly outperforms baseline approaches.

Evaluating and ranking the capabilities of different LLMs is crucial for understanding their performance and alignment with human preferences. Due to the high cost and time-consuming nature of human evaluations, an automatic LLM bencher (i.e., an automatic evaluation framework that aims to rank LLMs based on their alignment with human preferences) is indispensable. An automatic LLM bencher consists of four components: the input set (e.g., a user instruction), the evaluation model (e.g., an LLM), the evaluation type (e.g., pairwise comparison), and the aggregation method (e.g., the ELO rating system). However, previous work has not thoroughly explored how to select these components or how their different combinations influence the results. In this work, through controlled experiments, we provide a series of recommendations on how to choose each component to better automate the evaluation of LLMs. Furthermore, we discovered that when evaluating LLMs with similar performance, the performance of the automatic LLM bencher declines sharply, underscoring the limitations of current benchers and calling for future work. Lastly, we found that the evaluation models' performance at the instance level (e.g., the accuracy of selecting the best output) does not always align with their effectiveness when used as a component of a bencher, highlighting the importance of dedicated system-level evaluation of benchers.