arXiv:2601.11913v2 Announce Type: replace-cross Abstract: Effectively processing long contexts remains a fundamental yet unsolved challenge for large language models (LLMs). Existing single-LLM-based methods primarily reduce the context window or optimize the attention mechanism, but they often encounter additional computational costs or constrained expanded context length. While multi-agent-based frameworks can mitigate these limitations, they remain susceptible […]
The Rise of Verbal Tics in Large Language Models: A Systematic Analysis Across Frontier Models
arXiv:2604.19139v1 Announce Type: cross Abstract: As Large Language Models (LLMs) continue to evolve through alignment techniques such as Reinforcement Learning from Human Feedback (RLHF) and Constitutional AI, a growing and increasingly conspicuous phenomenon has emerged: the proliferation of verbal tics — repetitive, formulaic linguistic patterns that pervade model outputs. These range from sycophantic openers (“That’s […]
AutomationBench
arXiv:2604.18934v1 Announce Type: new Abstract: Existing AI benchmarks for software automation rarely combine cross-application coordination, autonomous API discovery, and policy adherence. Real business workflows demand all three: a single task may span a CRM, inbox, calendar, and messaging platform – requiring the agent to find the right endpoints, follow a policy document, and write correct […]
LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation
arXiv:2604.19167v1 Announce Type: cross Abstract: Deploying large language models (LLMs) in resource-constrained environments is hindered by heavy computational and memory requirements. We present LBLLM, a lightweight binarization framework that achieves effective W(1+1)A4 quantization through a novel three-stage quantization strategy. The framework proceeds as follows: (1) initialize a high-quality quantized model via PTQ; (2) quantize binarized […]
Debug2Fix: Can Interactive Debugging Help Coding Agents Fix More Bugs?
arXiv:2602.18571v2 Announce Type: replace-cross Abstract: While significant progress has been made in automating various aspects of software development through coding agents, there is still significant room for improvement in their bug fixing capabilities. Debugging and investigation of runtime behavior remains largely a manual, developer-driven process. Popular coding agents typically rely on either static analysis of […]
Attention-based Multi-modal Deep Learning Model of Spatio-temporal Crop Yield Prediction with Satellite, Soil and Climate Data
arXiv:2604.19217v1 Announce Type: cross Abstract: Crop yield prediction is one of the most important challenge, which is crucial to world food security and policy-making decisions. The conventional forecasting techniques are limited in their accuracy with reference to the fact that they utilize static data sources that do not reflect the dynamic and intricate relationships that […]
Personalized Benchmarking: Evaluating LLMs by Individual Preferences
arXiv:2604.18943v1 Announce Type: new Abstract: With the rise in capabilities of large language models (LLMs) and their deployment in real-world tasks, evaluating LLM alignment with human preferences has become an important challenge. Current benchmarks average preferences across all users to compute aggregate ratings, overlooking individual user preferences when establishing model rankings. Since users have varying […]
ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning
arXiv:2604.19254v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning (PEFT) reduces the training cost of full-parameter fine-tuning for large language models (LLMs) by training only a small set of task-specific parameters while freezing the pretrained backbone. However, existing approaches, such as Low-Rank Adaptation (LoRA), achieve adaptation by inserting independent low-rank perturbations directly to individual weights, resulting in […]
Fine-tuning DeepSeek-OCR-2 for Molecular Structure Recognition
arXiv:2604.03476v2 Announce Type: replace-cross Abstract: Optical Chemical Structure Recognition (OCSR) is critical for converting 2D molecular diagrams from printed literature into machine-readable formats. While Vision-Language Models have shown promise in end-to-end OCR tasks, their direct application to OCSR remains challenging, and direct full-parameter supervised fine-tuning often fails. In this work, we adapt DeepSeek-OCR-2 for molecular […]
IndiaFinBench: An Evaluation Benchmark for Large Language Model Performance on Indian Financial Regulatory Text
arXiv:2604.19298v1 Announce Type: cross Abstract: We introduce IndiaFinBench, to our knowledge the first publicly available evaluation benchmark for assessing large language model (LLM) performance on Indian financial regulatory text. Existing financial NLP benchmarks draw exclusively from Western financial corpora (SEC filings, US earnings reports, and English-language financial news), leaving a significant gap in coverage of […]
Reasoning Structure Matters for Safety Alignment of Reasoning Models
arXiv:2604.18946v1 Announce Type: new Abstract: Large reasoning models (LRMs) achieve strong performance on complex reasoning tasks but often generate harmful responses to malicious user queries. This paper investigates the underlying cause of these safety risks and shows that the issue lies in the reasoning structure itself. Based on this insight, we claim that effective safety […]
RDP LoRA: Geometry-Driven Identification for Parameter-Efficient Adaptation in Large Language Models
arXiv:2604.19321v1 Announce Type: cross Abstract: Fine-tuning Large Language Models (LLMs) remains structurally uncertain despite parameter-efficient methods such as Low-Rank Adaptation (LoRA), as the layer-specific roles of internal representations are poorly understood, leading to heuristic decisions about where adaptation should be applied. We model the evolution of hidden states as a high-dimensional geometric trajectory and propose […]