We present CadLLM, a training-free method to accelerate the inference throughput of diffusion-based LLMs (dLLMs). We first investigate on the dynamic nature of the token unmasking confidence across blocks and steps. Based on this observation, we then present a lightweight adaptive approach that can control the generation block size, step size, and threshold based on the average confidence score of the unmasked tokens. We further reduce the softmaxing overhead of token probability generation by dynamically leveraging a subset of vocabulary size to regulate sampling breadth. CadLLM is a plug-and-play model-agnostic with KV caching based dLLMs. Extensive experiments on four popular tasks demonstrate the efficacy of CadLLM to yield throughput improvement of up to 1.1-2.28x over the state-of-the-art baseline with competitive accuracy.

Demand for personalized financial advice is growing, yet current LLM-based advisors often fail to provide consistent and specialized guidance. Simple persona prompts rarely specify how a financial advisor should reason and often drift toward generic recommendations. We propose Fund2Persona, a framework that builds financial-advisor personas from real-world fund disclosures and refines them through an actor–scorer–patcher loop. We test whether the resulting personas can predict held-out portfolio changes and produce commentary consistent with fund managers’ own explanations. They outperform generic baselines on both tasks. We further study two downstream diagnostics: market-scenario generation, where persona retrieval broadens plausible investment views, and multi-turn investor–advisor conversations, where matched personas give more specific and useful advice than a generic advisor. These results suggest that real fund data can bring manager-specific investment expertise to LLM advisors rather than merely changing an LLM’s surface style.

Financial decision-makers face more information than they can directly inspect, making context compression necessary. Yet when large language models (LLMs) compress financial source material, they can alter the investment judgment supported by the original source. We frame this problem as information fidelity: compression loses fidelity when it changes the decision induced by the source. In agentic systems, such losses may recur across intermediate steps and amplify throughout the decision process. Across financial filings and earnings-call transcripts, we find that LLM-based compression can produce fluent and factually plausible compressed contexts that nevertheless alter downstream decisions. We analyze two diagnostic patterns associated with fidelity loss: decontextualization, where salient evidence is retained but separated from the caveats and contextual qualifiers needed for correct interpretation, and model dependency, where different compressors expose different views of the same source. We then propose Agentic Context Compression, which generates multiple candidate compressions and audits their disagreements against the original source. Our results suggest that financial compression should be evaluated not only by efficiency or factuality, but also by its ability to preserve decision-relevant context.

Natural language processing (NLP) has been widely used in quantitative finance, but traditional methods often struggle to capture rich narratives in textual data, leaving potentially informative signals under-explored. Large language models (LLMs) offer a promising alternative as they are able to extract nuanced semantics. In this paper, we ask whether semantic signals extracted by LLMs from corporate disclosures predict abnormal returns (alpha) beyond broad market movements and common risk factors. We introduce a simple framework, *LLM as extractor, embedding as ruler*, which extracts context-aware, metric-focused textual spans and quantifies semantic changes across consecutive disclosure periods using embedding similarity. This allows us to measure the degree of metric shifting - how much firms move away from previously emphasized metrics, referred to as moving targets. In portfolio and cross-sectional regression tests against a recent traditional baseline, our method yields a moving-targets signal that delivers significant risk-adjusted alpha. Qualitative analysis suggests that these gains stem from preserving contextual qualifiers and filtering out non-metric terms that traditional approaches often miss.

Advancements in Large Language Models (LLMs) and their increasing use in medical question-answering necessitate rigorous evaluation of their reliability. A critical challenge lies in hallucination, where models generate plausible yet factually incorrect outputs. In the medical domain, this poses serious risks to patient safety and clinical decision-making. To address this, we introduce MedHallu, one of the the first benchmark specifically designed for medical hallucination detection. MedHallu comprises 10,000 high-quality question-answer pairs derived from PubMedQA, with hallucinated answers systematically generated through a controlled pipeline. Our experiments show that state-of-the-art LLMs, including GPT-4o, Llama-3.1, and the medically fine-tuned UltraMedical, struggle with this binary hallucination detection task, with the best model achieving an F1 score as low as 0.625 for detecting ”hard” category hallucinations. Using bidirectional entailment clustering, we show that harder-to-detect hallucinations are semantically closer to ground truth. Through experiments, we also show incorporating domain-specific knowledge and introducing a ”not sure” category as one of the answer categories improves the precision and F1 scores by up to 38% relative to baselines.

Time series data are foundational in finance, healthcare, and energy domains. However, most existing methods and datasets remain focused on a narrow spectrum of tasks, such as forecasting or anomaly detection. To bridge this gap, we introduce Time Series Multi-Task Question Answering (Time-MQA), a unified framework that enables natural language queries across multiple time series tasks - numerical analytical tasks and open-ended question answering with reasoning. Central to Time-MQA is the TSQA dataset, a large-scale dataset containing ~200k question-answer pairs derived from diverse time series spanning environment, traffic, etc. This comprehensive resource covers various time series lengths and promotes robust model development. We further demonstrate how continually pre-training large language models (Mistral 7B, Llama-3 8B, and Qwen-2.5 7B) on the TSQA dataset enhanced time series reasoning capabilities, moving beyond mere numeric tasks and enabling more advanced and intuitive interactions with temporal data. The complete TSQA dataset, models, user study questionnaires for evaluation, and other related materials have been open-sourced here.

Traditionally, developing new language models (LMs) capable of addressing multiple tasks involves fine-tuning pre-trained LMs using a wide collection of datasets, a process that often incurs significant computational expenses. Model merging emerges as a cost-effective alternative, allowing the integration of existing models fine-tuned on different tasks into a single model that performs well across all tasks, eliminating the need for additional training. In this paper, we propose RankMean, an algorithm for merging fine-tuned LMs without requiring any downstream data. RankMean determines merging coefficients based on the relative rankings of weight change magnitudes and applies these coefficients for module-wise integration of various fine-tuned models. Our experimental results demonstrate that RankMean outperforms existing baseline methods on multiple benchmarks. The code is available at https://github.com/VITA-Group/RankMean.

Gigantic pre-trained models have become central to natural language processing (NLP), serving as the starting point for fine-tuning towards a range of downstream tasks. However, two pain points persist for this paradigm: (a) as the pre-trained models grow bigger (e.g., 175B parameters for GPT-3), even the fine-tuning process can be time-consuming and computationally expensive; (b) the fine-tuned model has the same size as its starting point by default, which is neither sensible due to its more specialized functionality, nor practical since many fine-tuned models will be deployed in resource-constrained environments. To address these pain points, we propose a framework for resource- and parameter-efficient fine-tuning by leveraging the sparsity prior in both weight updates and the final model weights. Our proposed framework, dubbed Dually Sparsity-Embedded Efficient Tuning (DSEE), aims to achieve two key objectives: (i) parameter efficient fine-tuning - by enforcing sparsity-aware low-rank updates on top of the pre-trained weights; and (ii) resource-efficient inference - by encouraging a sparse weight structure towards the final fine-tuned model. We leverage sparsity in these two directions by exploiting both unstructured and structured sparse patterns in pre-trained language models viaa unified approach. Extensive experiments and in-depth investigations, with diverse network backbones (i.e., BERT, RoBERTa, and GPT-2) on dozens of datasets, consistently demonstrate impressive parameter-/inference-efficiency, while maintaining competitive downstream performance. For instance, DSEE saves about 25% inference FLOPs while achieving comparable performance, with 0.5% trainable parameters on BERT. Codes are available at https://github.com/VITA-Group/DSEE.

Heavily overparameterized language models such as BERT, XLNet and T5 have achieved impressive success in many NLP tasks. However, their high model complexity requires enormous computation resources and extremely long training time for both pre-training and fine-tuning. Many works have studied model compression on large NLP models, but only focusing on reducing inference time while still requiring an expensive training process. Other works use extremely large batch sizes to shorten the pre-training time, at the expense of higher computational resource demands. In this paper, inspired by the Early-Bird Lottery Tickets recently studied for computer vision tasks, we propose EarlyBERT, a general computationally-efficient training algorithm applicable to both pre-training and fine-tuning of large-scale language models. By slimming the self-attention and fully-connected sub-layers inside a transformer, we are the first to identify structured winning tickets in the early stage of BERT training. We apply those tickets towards efficient BERT training, and conduct comprehensive pre-training and fine-tuning experiments on GLUE and SQuAD downstream tasks. Our results show that EarlyBERT achieves comparable performance to standard BERT, with 35 45% less training time. Code is available at https://github.com/VITA-Group/EarlyBERT.