Large Language Models have transformed the Contact Center industry, manifesting in enhanced self-service tools, streamlined administrative processes, and augmented agent productivity. This paper delineates our system that automates call driver generation, which serves as the foundation for tasks such as topic modeling, incoming call classification, trend detection, and FAQ generation, delivering actionable insights for contact center agents and administrators to consume. We present a cost-efficient LLM system design, with 1) a comprehensive evaluation of proprietary, open-weight, and fine-tuned models and 2) cost-efficient strategies, and 3) the corresponding cost analysis when deployed in production environments.

Fine-tuning Large Language Models (LLMs) on some task-specific datasets has been a primary use of LLMs. However, it has been empirically observed that this approach to enhancing capability inevitably compromises safety, a phenomenon also known as the safety-capability trade-off in LLM fine-tuning. This paper presents a theoretical framework for understanding the interplay between safety and capability in two primary safety-aware LLM fine-tuning strategies, providing new insights into the effects of data similarity, context overlap, and alignment loss landscape. Our theoretical results characterize the fundamental limits of the safety-capability trade-off in LLM fine-tuning, which are also validated by numerical experiments.

This paper surveys the development of large language model (LLM)-based agents for question answering (QA). Traditional agents face significant limitations, including substantial data requirements and difficulty in generalizing to new environments. LLM-based agents address these challenges by leveraging LLMs as their core reasoning engine. These agents achieve superior QA results compared to traditional QA pipelines and naive LLM QA systems by enabling interaction with external environments. We systematically review the design of LLM agents in the context of QA tasks, organizing our discussion across key stages: planning, question understanding, information retrieval, and answer generation. Additionally, this paper identifies ongoing challenges and explores future research directions to enhance the performance of LLM agent QA systems.

Large Language Models (LLMs) have made significant advances in various code-related tasks, particularly in generating source code from natural language descriptions (Zhao et al. (2023); Chang et al. (2024)). Their effectiveness is primarily driven by their extensive number of model parameters, the use of large and diverse datasets, and the immense computational resources employed during training (Kaplan et al. (2020)). These models are typically trained on vast corpora sourced from the web. LLMs are capable of capturing intricate patterns, linguistic subtleties, and semantic relationships. A wide range of models are available for code generation. There are general-purpose models like ChatGPT (Ouyang et al. (2022)), GPT -4 (Achiam et al. (2023)), and LLaMA (Touvron et al. (2023a)) which are designed for a broad range of applications, as well as specialized models such as StarCoder, Code LLaMA (Roziere et al. (2023)), DeepSeek-Coder, and Code Gemma that are optimized for code-related tasks. The integration of code generation with the latest advances in LLM technology is now an essential tool for many businesses, as well as an essential target for LLM developers as programming languages are considered to be different dialects of natural language (Athiwaratkun et al. (2022)).

Fine-tuning enables large language models (LLMs) to adapt to specific domains, but often undermines their previously established safety alignment. To mitigate the degradation of model safety during fine-tuning, we introduce LookAhead Tuning, which comprises two simple, low-resource, and effective data-driven methods that modify training data by previewing partial answer prefixes. Both methods aim to preserve the model's inherent safety mechanisms by minimizing perturbations to initial token distributions. Comprehensive experiments demonstrate that LookAhead Tuning effectively maintains model safety without sacrificing robust performance on downstream tasks. Our findings position LookAhead Tuning as a reliable and efficient solution for the safe and effective adaptation of LLMs. Code is released at https://github.com/zjunlp/LookAheadTuning.

Recent advancements in large language models (LLMs) have enabled their successful application to a broad range of tasks. However, in information-intensive tasks, the prompt length can grow fast, leading to increased computational requirements, performance degradation, and induced biases from irrelevant or redundant information. Recently, various prompt compression techniques have been introduced to optimize the trade-off between reducing input length and retaining performance. We propose a holistic evaluation framework that allows for in-depth analysis of prompt compression methods. We focus on three key aspects, besides compression ratio: (i) downstream task performance, (ii) grounding in the input context, and (iii) information preservation. Through this framework, we investigate state-of-the-art soft and hard compression methods, showing that they struggle to preserve key details from the original prompt, limiting their performance on complex tasks. We demonstrate that modifying soft prompting methods to control better the granularity of the compressed information can significantly improve their effectiveness -- up to +23\% in downstream task performance, more than +8 BERTScore points in grounding, and 2.7x more entities preserved in compression.

Every scientific discovery starts with an idea inspired by prior work, interdisciplinary concepts, and emerging challenges. Recent advancements in large language models (LLMs) trained on scientific corpora have driven interest in AI-supported idea generation. However, generating context-aware, high-quality, and innovative ideas remains challenging. We introduce SCI-IDEA, a framework that uses LLM prompting strategies and Aha Moment detection for iterative idea refinement. SCI-IDEA extracts essential facets from research publications, assessing generated ideas on novelty, excitement, feasibility, and effectiveness. Comprehensive experiments validate SCI-IDEA's effectiveness, achieving average scores of 6.84, 6.86, 6.89, and 6.84 (on a 1-10 scale) across novelty, excitement, feasibility, and effectiveness, respectively. Evaluations employed GPT-4o, GPT-4.5, DeepSeek-32B (each under 2-shot prompting), and DeepSeek-70B (3-shot prompting), with token-level embeddings used for Aha Moment detection. Similarly, it achieves scores of 6.87, 6.86, 6.83, and 6.87 using GPT-4o under 5-shot prompting, GPT-4.5 under 3-shot prompting, DeepSeek-32B under zero-shot chain-of-thought prompting, and DeepSeek-70B under 5-shot prompting with sentence-level embeddings. We also address ethical considerations such as intellectual credit, potential misuse, and balancing human creativity with AI-driven ideation. Our results highlight SCI-IDEA's potential to facilitate the structured and flexible exploration of context-aware scientific ideas, supporting innovation while maintaining ethical standards.

In this short report, we introduce joint multi-token prediction (JTP), a lightweight modification of standard next-token prediction designed to enrich hidden state representations by jointly predicting multiple future tokens. Unlike previous multi-token prediction approaches, JTP strategically employs teacher forcing of future-tokens through a carefully designed representation bottleneck, allowing the model to encode rich predictive information with minimal computational overhead during training. We show that the JTP approach achieves a short-horizon belief state representation, while popular alternatives for multi-token prediction fail to do so. We demonstrate the effectiveness of our method on the synthetic star graph navigation task from from Bachmann and Nagarajan [2024], highlighting a significant performance improvement over existing methods. This manuscript presents promising preliminary results intended to stimulate further research.

Proving Rubik's Cube theorems at the high level represents a notable milestone in human-level spatial imagination and logic thinking and reasoning. Traditional Rubik's Cube robots, relying on complex vision systems and fixed algorithms, often struggle to adapt to complex and dynamic scenarios. To overcome this limitation, we introduce CubeRobot, a novel vision-language model (VLM) tailored for solving 3x3 Rubik's Cubes, empowering embodied agents with multimodal understanding and execution capabilities. We used the CubeCoT image dataset, which contains multiple-level tasks (43 subtasks in total) that humans are unable to handle, encompassing various cube states. We incorporate a dual-loop VisionCoT architecture and Memory Stream, a paradigm for extracting task-related features from VLM-generated planning queries, thus enabling CubeRobot to independent planning, decision-making, reflection and separate management of high- and low-level Rubik's Cube tasks. Furthermore, in low-level Rubik's Cube restoration tasks, CubeRobot achieved a high accuracy rate of 100%, similar to 100% in medium-level tasks, and achieved an accuracy rate of 80% in high-level tasks.

Semantic segmentation has made significant strides in pixel-level image understanding, yet it remains limited in capturing contextual and semantic relationships between objects. Current models, such as CNN and Transformer-based architectures, excel at identifying pixel-level features but fail to distinguish semantically similar objects (e.g., "doctor" vs. "nurse" in a hospital scene) or understand complex contextual scenarios (e.g., differentiating a running child from a regular pedestrian in autonomous driving). To address these limitations, we proposed a novel Context-Aware Semantic Segmentation framework that integrates Large Language Models (LLMs) with state-of-the-art vision backbones. Our hybrid model leverages the Swin Transformer for robust visual feature extraction and GPT-4 for enriching semantic understanding through text embeddings. A Cross-Attention Mechanism is introduced to align vision and language features, enabling the model to reason about context more effectively. Additionally, Graph Neural Networks (GNNs) are employed to model object relationships within the scene, capturing dependencies that are overlooked by traditional models. Experimental results on benchmark datasets (e.g., COCO, Cityscapes) demonstrate that our approach outperforms the existing methods in both pixel-level accuracy (mIoU) and contextual understanding (mAP). This work bridges the gap between vision and language, paving the path for more intelligent and context-aware vision systems in applications including autonomous driving, medical imaging, and robotics.