Related papers: DYCP: Dynamic Context Pruning for Long-Form Dialog…
Large language models (LLMs), despite their impressive performance in various language tasks, are typically limited to processing texts within context-window size. This limitation has spurred significant research efforts to enhance LLMs'…
Multi-turn dialogue is the predominant form of interaction with large language models (LLMs). While LLM routing is effective in single-turn settings, existing methods fail to maximize cumulative performance in multi-turn dialogue due to…
Built upon the existing analysis of retrieval heads in large language models, we propose an alternative reranking framework that trains models to estimate passage-query relevance using the attention scores of selected heads. This approach…
Recently, substantial advancements in pre-trained vision-language models have greatly enhanced the capabilities of multi-modal dialog systems. These models have demonstrated significant improvements by fine-tuning on downstream tasks.…
In-Context Learning and Chain-of-Thought prompting improve reasoning in large language models (LLMs). These typically come at the cost of longer, more expensive prompts that may contain redundant information. Prompt compression based on…
Few-shot dialogue state tracking (DST) with Large Language Models (LLM) relies on an effective and efficient conversation retriever to find similar in-context examples for prompt learning. Previous works use raw dialogue context as search…
Long context inference scenarios have become increasingly important for large language models, yet they introduce significant computational latency. While prior research has optimized long-sequence inference through operators, model…
As large language models (LLMs) increasingly permeate daily lives, there is a growing demand for real-time interactions that mirror human conversations. Traditional turn-based chat systems driven by LLMs prevent users from verbally…
Large language models (LLMs) have achieved impressive performance in text summarization, yet their performance often falls short when applied to specialized domains that differ from their original pre-training distribution. While…
Discrete Combinatorial Problems (DCPs) are prevalent in industrial decision-making and optimisation. However, while constraint solving technologies for DCPs have advanced significantly, the core process of formalising them, namely…
Large language models (LLMs) exhibit diverse response behaviors, costs, and strengths, making it challenging to select the most suitable LLM for a given user query. We study the problem of adaptive multi-LLM selection in an online setting,…
The rapid evolution of large language models (LLMs) has transformed conversational agents, enabling complex human-machine interactions. However, evaluation frameworks often focus on single tasks, failing to capture the dynamic nature of…
Conversations are always related to certain topics. However, it is challenging to fuse dialogue history and topic information from various sources at the same time in current dialogue generation models because of the input length limit of…
The integration of extensive, dynamic knowledge into Large Language Models (LLMs) remains a significant challenge due to the inherent entanglement of factual data and reasoning patterns. Existing solutions, ranging from non-parametric…
This paper presents Dynamic Context Prompting/Programming (DCP/P), a novel framework for interacting with LLMs to generate graph-based content with a dynamic context window history. While there is an existing study utilizing LLMs to…
Large language models (LLMs) have demonstrated self-improvement capabilities via feedback and refinement, but current small language models (SLMs) have had limited success in this area. Existing correction approaches often rely on…
Large language models (LLMs) face significant challenges in handling long-context tasks because of their limited effective context window size during pretraining, which restricts their ability to generalize over extended sequences.…
Conversational systems based on Large Language Models (LLMs), such as ChatGPT, show exceptional proficiency in context understanding and response generation. However, despite their impressive capabilities, they still possess limitations,…
Long-context inference for Large Language Models (LLMs) is heavily limited by high computational demands. While several existing methods optimize attention computation, they still process the full set of hidden states at each layer,…
Current end-to-end retrieval-based dialogue systems are mainly based on Recurrent Neural Networks or Transformers with attention mechanisms. Although promising results have been achieved, these models often suffer from slow inference or…