相关论文: Large Language Models as Amortized Pareto-Front Ge…
Large language models (LLMs) demonstrate remarkable text comprehension and generation capabilities but often lack the ability to utilize up-to-date or domain-specific knowledge not included in their training data. To address this gap, we…
Prompt engineering, as an efficient and effective way to leverage Large Language Models (LLM), has drawn a lot of attention from the research community. The existing research primarily emphasizes the importance of adapting prompts to…
Diffusion language models (DLMs) promise parallel, order-agnostic generation, but on standard benchmarks they have historically lagged behind autoregressive models in sample quality and diversity. Recent continuous flow and diffusion…
Automated optimization modeling via Large Language Models (LLMs) has emerged as a promising approach to assist complex human decision-making. While post-training has become a pivotal technique to enhance LLMs' capabilities in this domain,…
The automatic generation of counter-speech (CS) is a critical strategy for addressing hate speech by providing constructive and informed responses. However, existing methods often fail to generate high-quality, impactful, and scalable CS,…
Large Language Models (LLMs), particularly smaller variants, still struggle with complex reasoning tasks. While inference-time prompting can guide reasoning, existing methods often rely on sequential queries. Ensemble approaches offer a…
Simultaneous speech translation requires accurate segmentation to balance translation quality and latency. Recent studies such as SHAS have introduced pretrained segmentation models, achieving stronger performance than heuristic rules.…
Large language models (LLMs) have achieved substantial progress in processing long contexts but still struggle with long-context reasoning. Existing approaches typically involve fine-tuning LLMs with synthetic data, which depends on…
Large language models (LLMs) demonstrate remarkable capabilities but face deployment challenges due to their massive parameter counts. While existing compression techniques like pruning can reduce model size, it leads to significant…
Recent advanced large language models (LLMs) have showcased their emergent capability of in-context learning, facilitating intelligent decision-making through natural language prompts without retraining. This new machine learning paradigm…
Autoregressive large language models (LLMs) compress knowledge from their training data through next-token conditional distributions. This limits tractable querying of this knowledge to start-to-end autoregressive sampling. However, many…
Large Language Models (LLMs) have demonstrated impressive capabilities in reasoning tasks, yet their reliance on static prompt structures and limited adaptability to complex scenarios remains a significant challenge. In this paper, we…
Significantly simplifying the creation of optimization models for real-world business problems has long been a major goal in applying mathematical optimization more widely to important business and societal decisions. The recent…
Direct Multisearch (DMS) is a Derivative-free Optimization class of algorithms suited for computing approximations to the complete Pareto front of a given Multiobjective Optimization problem. It has a well-supported convergence analysis and…
Autonomous driving demands safe motion planning, especially in critical "long-tail" scenarios. Recent end-to-end autonomous driving systems leverage large language models (LLMs) as planners to improve generalizability to rare events.…
We present an outcome-driven fine-tuning framework that enhances the forecasting capabilities of large language models (LLMs) without relying on human-curated reasoning samples. Our method leverages model self-play to generate pairs of…
Gradient-free prompt optimization methods have made significant strides in enhancing the performance of closed-source Large Language Models (LLMs) across a wide range of tasks. However, existing approaches make light of the importance of…
Large Language Models (LLM) are usually fine-tuned to participate in dyadic or two-party dialogues, which can not adapt well to multi-party dialogues (MPD), which hinders their applications in such scenarios including multi-personal…
Large language models (LLMs) commonly employ autoregressive generation during inference, leading to high memory bandwidth demand and consequently extended latency. To mitigate this inefficiency, we present Bi-directional Tuning for lossless…
Large Language Models (LLMs) exhibit remarkable proficiency in addressing a diverse array of tasks within the Natural Language Processing (NLP) domain, with various prompt design strategies significantly augmenting their capabilities.…