相关论文: Textual Self-attention Network: Test-Time Preferen…
Prompt optimization improves the reasoning abilities of large language models (LLMs) without requiring parameter updates to the target model. Following heuristic-based "Think step by step" approaches, the field has evolved in two main…
Large Language Models (LLMs) tend to generate a long reasoning chain when solving complex tasks. However, as the reasoning chain extends, critical intermediate steps and the original prompt will be buried in the context, receiving…
While textless Spoken Language Models (SLMs) have shown potential in end-to-end speech-to-speech modeling, they still lag behind text-based Large Language Models (LLMs) in terms of semantic coherence and relevance. This work introduces the…
Large language models (LLMs) have demonstrated remarkable capabilities in handling complex dialogue tasks without requiring use case-specific fine-tuning. However, analyzing live dialogues in real-time necessitates low-latency processing…
Multimodal Sentiment Analysis (MSA) endeavors to understand human sentiment by leveraging language, visual, and acoustic modalities. Despite the remarkable performance exhibited by previous MSA approaches, the presence of inherent…
Aligning large language models (LLMs) with diverse and multifaceted user preferences is a fundamental challenge in personalized AI systems. Existing multi-objective alignment methods either rely on costly training or require pre-trained…
Large language models (LLMs) are increasingly being used as decision aids. However, users have diverse values and preferences that can affect their decision-making, which requires novel methods for LLM alignment and personalization.…
Self-Rewarding Language Models propose an architecture in which the Large Language Models(LLMs) both generates responses and evaluates its own outputs via LLM-as-a-Judge prompting, dynamically improving its generative capabilities through…
In the realm of Text-Based Person Search (TBPS), mainstream methods aim to explore more efficient interaction frameworks between text descriptions and visual data. However, recent approaches encounter two principal challenges. Firstly, the…
Pre-trained large-scale language models (LLMs) excel at producing coherent articles, yet their outputs may be untruthful, toxic, or fail to align with user expectations. Current approaches focus on using reinforcement learning with human…
Recurrent neural nets (RNN) and convolutional neural nets (CNN) are widely used on NLP tasks to capture the long-term and local dependencies, respectively. Attention mechanisms have recently attracted enormous interest due to their highly…
Multimodal Sentiment Analysis (MSA) aims to mine sentiment information from text, visual, and acoustic modalities. Previous works have focused on representation learning and feature fusion strategies. However, most of these efforts ignored…
Large language models (LLMs), endowed with exceptional reasoning capabilities, are adept at discerning profound user interests from historical behaviors, thereby presenting a promising avenue for the advancement of recommendation systems.…
With the development of large language models (LLMs), there has been an increasing need for significant advancements in handling long contexts. To enhance long-context capabilities, constructing high-quality training data with long-range…
Aligning text-to-speech (TTS) system outputs with human feedback through preference optimization has been shown to effectively improve the robustness and naturalness of language model-based TTS models. Current approaches primarily require…
Although humans inherently have diverse values, current large language model (LLM) alignment methods often assume that aligning LLMs with the general public's preferences is optimal. A major challenge in adopting a more individualized…
Finding preferences expressed in natural language is an important but challenging task. State-of-the-art(SotA) methods leverage transformer-based models such as BERT, RoBERTa, etc. and graph neural architectures such as graph attention…
Large Language Model (LLM) agents are commonly tuned with supervised finetuning on ReAct-style expert trajectories or preference optimization over pairwise rollouts. Most of these methods focus on imitating specific expert behaviors or…
Despite large language models (LLMs) have achieved impressive achievements across numerous tasks, supervised fine-tuning (SFT) remains essential for adapting these models to specialized domains. However, SFT for domain specialization can be…
The efficient implementation of large language models (LLMs) is crucial for deployment on resource-constrained devices. Low-rank tensor compression techniques, such as tensor-train (TT) networks, have been widely studied for…