Table Question Answering (TQA) involves retrieving relevant tables from a large corpus to answer natural language queries. Traditional dense retrieval models, such as DTR and ColBERT, not only incur high computational costs for large-scale retrieval tasks but also require retraining or fine-tuning on new datasets, limiting their adaptability to evolving domains and knowledge. In this work, we propose $\textbf{CRAFT}$, a cascaded retrieval approach that first uses a sparse retrieval model to filter a subset of candidate tables before applying more computationally expensive dense models and neural re-rankers. Our approach achieves better retrieval performance than state-of-the-art (SOTA) sparse, dense, and hybrid retrievers. We further enhance table representations by generating table descriptions and titles using Gemini Flash 1.5. End-to-end TQA results using various Large Language Models (LLMs) on NQ-Tables, a subset of the Natural Questions Dataset, demonstrate $\textbf{CRAFT}$ effectiveness.

Recent Large Reasoning Models (LRMs) have shown substantially improved reasoning capabilities over traditional Large Language Models (LLMs) by incorporating extended thinking processes prior to producing final responses. However, excessively lengthy thinking introduces substantial overhead in terms of token consumption and latency, which is particularly unnecessary for simple queries. In this work, we introduce Large Hybrid-Reasoning Models (LHRMs), the first kind of model capable of adaptively determining whether to perform thinking based on the contextual information of user queries. To achieve this, we propose a two-stage training pipeline comprising Hybrid Fine-Tuning (HFT) as a cold start, followed by online reinforcement learning with the proposed Hybrid Group Policy Optimization (HGPO) to implicitly learn to select the appropriate thinking mode. Furthermore, we introduce a metric called Hybrid Accuracy to quantitatively assess the model's capability for hybrid thinking. Extensive experimental results show that LHRMs can adaptively perform hybrid thinking on queries of varying difficulty and type. It outperforms existing LRMs and LLMs in reasoning and general capabilities while significantly improving efficiency. Together, our work advocates for a reconsideration of the appropriate use of extended thinking processes and provides a solid starting point for building hybrid thinking systems.

Clickstream data from digital learning environments offer valuable insights into students' learning behaviors, but are challenging to interpret due to their high dimensionality and granularity. Prior approaches have relied mainly on handcrafted features, expert labeling, clustering, or supervised models, therefore often lacking generalizability and scalability. In this work, we introduce ClickSight, an in-context Large Language Model (LLM)-based pipeline that interprets student clickstreams to reveal their learning strategies. ClickSight takes raw clickstreams and a list of learning strategies as input and generates textual interpretations of students' behaviors during interaction. We evaluate four different prompting strategies and investigate the impact of self-refinement on interpretation quality. Our evaluation spans two open-ended learning environments and uses a rubric-based domain-expert evaluation. Results show that while LLMs can reasonably interpret learning strategies from clickstreams, interpretation quality varies by prompting strategy, and self-refinement offers limited improvement. ClickSight demonstrates the potential of LLMs to generate theory-driven insights from educational interaction data.

As large language models (LLMs) are increasingly deployed in high-stakes settings, their ability to refuse ethically sensitive prompts-such as those involving hate speech or illegal activities-has become central to content moderation and responsible AI practices. While refusal responses can be viewed as evidence of ethical alignment and safety-conscious behavior, recent research suggests that users may perceive them negatively. At the same time, automated assessments of model outputs are playing a growing role in both evaluation and training. In particular, LLM-as-a-Judge frameworks-in which one model is used to evaluate the output of another-are now widely adopted to guide benchmarking and fine-tuning. This paper examines whether such model-based evaluators assess refusal responses differently than human users. Drawing on data from Chatbot Arena and judgments from two AI judges (GPT-4o and Llama 3 70B), we compare how different types of refusals are rated. We distinguish ethical refusals, which explicitly cite safety or normative concerns (e.g., "I can't help with that because it may be harmful"), and technical refusals, which reflect system limitations (e.g., "I can't answer because I lack real-time data"). We find that LLM-as-a-Judge systems evaluate ethical refusals significantly more favorably than human users, a divergence not observed for technical refusals. We refer to this divergence as a moderation bias-a systematic tendency for model-based evaluators to reward refusal behaviors more than human users do. This raises broader questions about transparency, value alignment, and the normative assumptions embedded in automated evaluation systems.

Information extraction (IE) plays a crucial role in natural language processing (NLP) by converting unstructured text into structured knowledge. Deploying computationally intensive large language models (LLMs) on resource-constrained devices for information extraction is challenging, particularly due to issues like hallucinations, limited context length, and high latency-especially when handling diverse extraction schemas. To address these challenges, we propose a two-stage information extraction approach adapted for on-device LLMs, called Dual-LoRA with Incremental Schema Caching (DLISC), which enhances both schema identification and schema-aware extraction in terms of effectiveness and efficiency. In particular, DLISC adopts an Identification LoRA module for retrieving the most relevant schemas to a given query, and an Extraction LoRA module for performing information extraction based on the previously selected schemas. To accelerate extraction inference, Incremental Schema Caching is incorporated to reduce redundant computation, substantially improving efficiency. Extensive experiments across multiple information extraction datasets demonstrate notable improvements in both effectiveness and efficiency.

LLM-based annotation has become something of an academic Wild West: the lack of established practices and standards has led to concerns about the quality and validity of research. Researchers have warned that the ostensible simplicity of LLMs can be misleading, as they are prone to bias, misunderstandings, and unreliable results [1, p.1]. LLMs outperform typical human annotators. The evidence is consistent across different types of texts and time periods. It strongly suggests that ChatGPT may already be a superior approach compared to crowd annotations on platforms such as MTurk. At the very least, the findings demonstrate the importance of studying the text-annotation properties and capabilities of LLMs more in depth [2, p.2]. Together, these contrasting perspectives highlight the need to critically examine large language models (LLMs) for text annotation and classification. Although human annotation remains widespread, it poses considerable challenges. It is time-consuming and costly--up to $5 per annotation and $50 per hour for annotators [3]--and often suffers from inconsistencies stemming from the intricacies of language and the subjectivity of annotators [4].

This work aims to demystify the out-of-distribution (OOD) capabilities of in-context learning (ICL) by studying linear regression tasks parameterized with low-rank covariance matrices. With such a parameterization, we can model distribution shifts as a varying angle between the subspace of the training and testing covariance matrices. We prove that a single-layer linear attention model incurs a test risk with a non-negligible dependence on the angle, illustrating that ICL is not robust to such distribution shifts. However, using this framework, we also prove an interesting property of ICL: when trained on task vectors drawn from a union of low-dimensional subspaces, ICL can generalize to any subspace within their span, given sufficiently long prompt lengths. This suggests that the OOD generalization ability of Transformers may actually stem from the new task lying within the span of those encountered during training. We empirically show that our results also hold for models such as GPT-2, and conclude with (i) experiments on how our observations extend to nonlinear function classes and (ii) results on how LoRA has the ability to capture distribution shifts.

This paper explores generalised probabilistic modelling and uncertainty estimation in comparative LLM-as-a-judge frameworks. We show that existing Product-of-Experts methods are specific cases of a broader framework, enabling diverse modelling options. Furthermore, we propose improved uncertainty estimates for individual comparisons, enabling more efficient selection and achieving strong performance with fewer evaluations. We also introduce a method for estimating overall ranking uncertainty. Finally, we demonstrate that combining absolute and comparative scoring improves performance. Experiments show that the specific expert model has a limited impact on final rankings but our proposed uncertainty estimates, especially the probability of reordering, significantly improve the efficiency of systems reducing the number of needed comparisons by ~50%. Furthermore, ranking-level uncertainty metrics can be used to identify low-performing predictions, where the nature of the probabilistic model has a notable impact on the quality of the overall uncertainty.

Uncertainty estimation remains a critical challenge in adapting pre-trained language models to classification tasks, particularly under parameter-efficient fine-tuning approaches such as adapters. We introduce AdUE1, an efficient post-hoc uncertainty estimation (UE) method, to enhance softmax-based estimates. Our approach (1) uses a differentiable approximation of the maximum function and (2) applies additional regularization through L2-SP, anchoring the fine-tuned head weights and regularizing the model. Evaluations on five NLP classification datasets across four language models (RoBERTa, ELECTRA, LLaMA-2, Qwen) demonstrate that our method consistently outperforms established baselines such as Mahalanobis distance and softmax response. Our approach is lightweight (no base-model changes) and produces better-calibrated confidence.

Reinforcement Learning (RL) algorithms sample multiple n>1 solution attempts for each problem and reward them independently. This optimizes for pass@1 performance and prioritizes the strength of isolated samples at the expense of the diversity and collective utility of sets of samples. This under-utilizes the sampling capacity, limiting exploration and eventual improvement on harder examples. As a fix, we propose Pass-at-k Policy Optimization (PKPO), a transformation on the final rewards which leads to direct optimization of pass@k performance, thus optimizing for sets of samples that maximize reward when considered jointly. Our contribution is to derive novel low variance unbiased estimators for pass@k and its gradient, in both the binary and continuous reward settings. We show optimization with our estimators reduces to standard RL with rewards that have been jointly transformed by a stable and efficient transformation function. While previous efforts are restricted to k=n, ours is the first to enable robust optimization of pass@k for any arbitrary k <= n. Moreover, instead of trading off pass@1 performance for pass@k gains, our method allows annealing k during training, optimizing both metrics and often achieving strong pass@1 numbers alongside significant pass@k gains. We validate our reward transformations on toy experiments, which reveal the variance reducing properties of our formulations. We also include real-world examples using the open-source LLM, GEMMA-2. We find that our transformation effectively optimizes for the target k. Furthermore, higher k values enable solving more and harder problems, while annealing k boosts both the pass@1 and pass@k . Crucially, for challenging task sets where conventional pass@1 optimization stalls, our pass@k approach unblocks learning, likely due to better exploration by prioritizing joint utility over the utility of individual samples.