Related papers: Task-agnostic Prompt Compression with Context-awar…
Retrieval-augmented generation improves the factual accuracy of Large Language Models (LLMs) by incorporating external context, but often suffers from irrelevant retrieved content that hinders effectiveness. Context compression addresses…
Recent advances have shown that optimizing prompts for Large Language Models (LLMs) can significantly improve task performance, yet many optimization techniques rely on heuristics or manual exploration. We present LatentPrompt, a…
Large Language Models (LLMs) face significant computational challenges when processing long contexts due to the quadratic complexity of self-attention. While soft context compression methods, which map input text to smaller latent…
Prompt Tuning has been a popular Parameter-Efficient Fine-Tuning method attributed to its remarkable performance with few updated parameters on various large-scale pretrained Language Models (PLMs). Traditionally, each prompt has been…
Retrieval-augmented generation supports language models to strengthen their factual groundings by providing external contexts. However, language models often face challenges when given extensive information, diminishing their effectiveness…
In-context learning has established itself as an important learning paradigm for Large Language Models (LLMs). In this paper, we demonstrate that LLMs can learn encoding keys in-context and perform analysis directly on encoded…
Long context inference presents challenges at the system level with increased compute and memory requirements, as well as from an accuracy perspective in being able to reason over long contexts. Recently, several methods have been proposed…
Prompt engineering enables Large Language Models (LLMs) to perform a variety of tasks. However, lengthy prompts significantly increase computational complexity and economic costs. To address this issue, we study six prompt compression…
Prompt tuning (PT) offers a cost-effective alternative to fine-tuning large-scale pre-trained language models (PLMs), requiring only a few parameters in soft prompt tokens added before the input text. However, existing PT approaches face…
Large Vision-Language Models (LVLMs) excel in visual understanding and reasoning, but the excessive visual tokens lead to high inference costs. Although recent token reduction methods mitigate this issue, they mainly target single-turn…
With the rising popularity of Transformer-based large language models (LLMs), reducing their high inference costs has become a significant research focus. One effective approach is to compress the long input contexts. Existing methods…
In long context scenarios, large language models (LLMs) face three main challenges: higher computational cost, performance reduction, and position bias. Research indicates that LLM performance hinges on the density and position of key…
Prompt engineering is crucial for achieving reliable and effective outputs from large language models (LLMs), but its design requires specialized knowledge of prompting techniques and a deep understanding of target tasks. To address this…
Multi-task language models show outstanding performance for various natural language understanding tasks with only a single model. However, these language models utilize an unnecessarily large number of model parameters, even when used only…
Prompt compression is an innovative method for efficiently condensing input prompts while preserving essential information. To facilitate quick-start services, user-friendly interfaces, and compatibility with common datasets and metrics, we…
Existing Multimodal Large Language Models (MLLMs) process a large number of visual tokens, leading to significant computational costs and inefficiency. Instruction-related visual token compression demonstrates strong task relevance, which…
Large Language Models (LLMs) have improved substantially alignment, yet their behavior remains highly sensitive to prompt phrasing. This brittleness has motivated automated prompt engineering, but most existing methods (i) require a…
We explore the idea of compressing the prompts used to condition language models, and show that compressed prompts can retain a substantive amount of information about the original prompt. For severely compressed prompts, while fine-grained…
Generating realistic synthetic tabular data presents a critical challenge in machine learning. It adds another layer of complexity when this data contain class imbalance problems. This paper presents a novel token-aware data imputation…
Transformer-based language models (LMs) are powerful and widely-applicable tools, but their usefulness is constrained by a finite context window and the expensive computational cost of processing long text documents. We propose to adapt…