With the prevalence of Large Language Models (LLMs), Text-to-SQL has made significant progress, yet applying it to massive, real-world databases remains a challenge. While previous works adopt a retrieve-then-generate framework, they struggle with the profound semantic gap between user queries and vague schema definitions. Existing methods relying on unidirectional query expansion often fail to bridge lexical mismatches, while graph-based approaches struggle to navigate schemas when explicit structural links (e.g., foreign keys) are missing. To address this, we propose Bi-SR, a retrieval framework that bridges this gap through a bidirectional semantic enhancement strategy. We simultaneously enrich vague table schemas offline and perform online generative query expansion—specifically predicting potential schema structures—to align user intent. Crucially, we introduce a dual-augmented contrastive training objective for the dense retriever, which trains the dense retriever to recognize the semantic correspondence between the LLM-expanded query intent and the detailed schema descriptions. Experiments on massive schema routing benchmarks constructed from BIRD and Spider demonstrate that Bi-SR achieves state-of-the-art performance and significantly empowers smaller models for cost-effective deployment.

Large Reasoning Models (LRMs) achieve strong performance on complex tasks through extended chains of thought but suffer from high inference latency due to autoregressive reasoning. Recent work explores using Small Reasoning Models (SRMs) to accelerate LRM inference, yet existing frameworks such as SpecReason adopt a polling-based design that repeatedly invokes the LRM for verification at every step. This approach is inefficient, as frequent LRM calls introduce a high computational overhead, and is unreliable, since the LRM as a judge is prone to errors. In this paper, we systematically characterize the capability boundaries of SRMs and identify three common types of reasoning risks: (1) path divergence, where SRMs lack the strategic ability to construct an initial plan, causing reasoning to deviate from the most probable path; (2) cognitive overload, where SRMs fail to solve particularly difficult steps; and (3) recovery inability, where SRMs lack robust self-reflection and error correction mechanisms. To address these challenges, we propose TrigReason, a trigger-based collaborative reasoning framework that replaces continuous polling with selective intervention. TrigReason delegates most reasoning to the SRM and activates LRM intervention only when necessary—during initial strategic planning (strategic priming trigger), upon detecting extraordinary overconfidence (cognitive offload trigger), or when reasoning falls into unproductive loops (intervention request trigger). The evaluation results on AIME24, AIME25, and GPQA-D indicate that TrigReason matches the accuracy of full LRMs and SpecReason, while offloading 1.70×–4.79× more reasoning steps to SRMs. Under edge–cloud conditions, TrigReason reduces latency by 43.9% and API cost by 73.3% compared to SpecReason.

As machine learning (ML) application continues to expand across diverse fields, there is a rising demand for ML code generation. In this paper, we aim at a critical research question: Can machines autonomously generate ML code for sophisticated, human-designed algorithms or solutions? To answer this question, we introduce a novel benchmark, MLAlgo-Bench, which includes two challenging tasks: 1) Generating code for ML algorithms including both traditional ML and modern deep learning-based methods, and 2) Giving humans solution sketches, writing ML code for solving practical tasks in Kaggle competitions. This benchmark is unique in its focus on the challenges of interpreting intricate human instructions and producing multi-step, high-complexity code, offering a rigorous test for current Large Language Model (LLM) capabilities. We introduce an automatic evaluation framework with comprehensive metrics such as task pass rate, relative performance metric, and time overhead. Currently, the top-performing models (Claude3.5-Sonet) achieve a 48.8% task completion rate on realizing machine learning algorithms, and a 21.6% rate for completing Kaggle competitions. Further analysis suggests substantial room for improvement.

KV Cache is commonly used to accelerate LLM inference with long contexts, yet its high memory demand drives the need for cache compression. Existing compression methods, however, are largely heuristic and lack dynamic budget allocation. To address this limitation, we introduce a unified framework for cache compression by minimizing information loss in Transformer residual streams. Building on it, we analyze the layer attention output loss and derive a new metric to compare cache entries across heads, enabling layer-wise compression with dynamic head budgets. Additionally, by contrasting cross-layer information, we also achieve dynamic layer budgets. LAVa is the first unified strategy for cache eviction and dynamic budget allocation that, unlike prior methods, does not rely on training or the combination of multiple strategies. Experiments with four benchmarks (LongBench, Needle-In-A-Haystack, Ruler, and InfiniteBench) demonstrate its superiority over strong baselines. Moreover, our experiments reveal a new insight: dynamic layer budgets are crucial for generation tasks (e.g., code completion), while dynamic head budgets play a key role in extraction tasks (e.g., extractive QA). As a fully dynamic compression method, LAVa consistently maintains top performance across task types.

The synergistic mechanism based on Speculative Decoding (SD) has garnered considerable attention as a simple yet effective approach for accelerating the inference of large language models (LLMs). Nonetheless, the high rejection rates require repeated LLMs calls to validate draft tokens, undermining the overall efficiency gain of SD.In this work, we revisit existing verification mechanisms and propose a novel synergetic mechanism Consultant Decoding (CD). CD achieves up to a 2.5-fold increase in inference speed compared to the target model, while maintaining comparable generation quality (~100% of the target model’s performance). Interestingly, this is achieved by combining models whose parameter sizes differ by two orders of magnitude.In addition, CD reduces the call frequency of the large target model to below 10%, particularly in more demanding tasks.CD’s performance was even found to surpass that of the large target model, which theoretically represents the upper bound for speculative decoding.

Large language models (LLMs) have demonstrated exceptional performance across various applications, but their conversational abilities decline sharply as model size decreases, presenting a barrier to their deployment in resource-constrained environments. Knowledge distillation (KD) with Direct Preference Optimization (DPO) has emerged as a promising approach to enhance the conversational abilities of smaller models using a larger teacher model. However, current methods primarily focus on “black-box” KD, which only uses the teacher’s responses, overlooking the rich distributional information within the teacher’s probability distribution. This paper addresses this gap by introducing daDPO (Distillation-Aware DPO), a novel framework that integrates the teacher’s distributional information into DPO distillation while preserving theoretical guarantees. Our framework offers a unified objective that enhances both preference optimization and distribution-based distillation. We provide rigorous theoretical analysis and empirical validation, showing that daDPO outperforms existing methods in restoring performance for pruned models and enhancing smaller models within the same LLM family. Notably, in in-domain evaluation, our method enables a 20% pruned Vicuna1.5-7B to achieve near-teacher performance (-7.3% preference rate), and allows Qwen2.5-1.5B to occasionally outperform its 7b teacher model (14.0% win rate).

This paper describes two models that employ word frequency embeddings to deal with the problem of readability assessment in multiple languages. The task is to determine the difficulty level of a given document, i.e., how hard it is for a reader to fully comprehend the text. The proposed models show how frequency information can be integrated to improve the readability assessment. The experimental results testing on both English and Chinese datasets show that the proposed models improve the results notably when comparing to those using only traditional word embeddings.