相关论文: ContextFocus: Activation Steering for Contextual F…

Large language models (LLMs) tend to inadequately integrate input context during text generation, relying excessively on encoded prior knowledge in model parameters, potentially resulting in generated text with factual inconsistencies or…

Transformer-based language models (LMs) track contextual information through large, hard-coded input windows. We introduce MemoryPrompt, a leaner approach in which the LM is complemented by a small auxiliary recurrent network that passes…

Semantic caching significantly reduces computational costs and improves efficiency by storing and reusing large language model (LLM) responses. However, existing systems rely primarily on matching individual queries, lacking awareness of…

Current LLM agents typically lack instance-level context, which comprises concrete facts such as environment structure, system configurations, and local mechanics. Consequently, existing methods are forced to intertwine exploration with…

Contextual-LAS (CLAS) has been shown effective in improving Automatic Speech Recognition (ASR) of rare words. It relies on phrase-level contextual modeling and attention-based relevance scoring without explicit contextual constraint which…

Large Language Models (LLMs) excel across a variety of language tasks yet are constrained by limited input lengths and high computational costs. Existing approaches\textemdash such as relative positional encodings (e.g., RoPE, ALiBi) and…

The large language model (LLM)-as-judge paradigm has been used to meet the demand for a cheap, reliable, and fast evaluation of model outputs during AI system development and post-deployment monitoring. While judge models -- LLMs finetuned…

Process reward models (PRMs) have demonstrated significant efficacy in enhancing the mathematical reasoning capabilities of large language models (LLMs) by leveraging test-time scaling (TTS). However, while most PRMs exhibit substantial…

Incorporating external context can significantly enhance the response quality of Large Language Models (LLMs). However, real-world contexts often mix relevant information with disproportionate inappropriate content, posing reliability…

In-Context Learning (ICL) enables large language models (LLMs) to achieve rapid task adaptation by learning from demonstrations. With the increase in available context length of LLMs, recent experiments have shown that the performance of…

The Neural Contextual Reinforcement Framework introduces an innovative approach to enhancing the logical coherence and structural consistency of text generated by large language models. Leveraging reinforcement learning principles, the…

When performing tasks like automatic speech recognition or spoken language understanding for a given utterance, access to preceding text or audio provides contextual information can improve performance. Considering the recent advances in…

Knowledge augmentation has significantly enhanced the performance of Large Language Models (LLMs) in knowledge-intensive tasks. However, existing methods typically operate on the simplistic premise that model performance equates with…

Large language models (LLMs) often struggle with context fidelity, producing inconsistent answers when responding to questions based on provided information. Existing approaches either rely on expensive supervised fine-tuning to generate…

Progress on training and architecture strategies has enabled LLMs with millions of tokens in context length. However, empirical evidence suggests that such long-context LLMs can consume far more text than they can reliably use. On the other…

Faithful generation in large language models (LLMs) is challenged by knowledge conflicts between parametric memory and external context. Existing contrastive decoding methods tuned specifically to handle conflict often lack adaptability and…

Large Language Models (LLMs) demonstrate proficiency across diverse tasks but often require targeted adaptations for specific applications. Various methods have been proposed to facilitate this adaptation, including fewshot fine-tuning,…

We propose ContextRL, a novel framework that leverages context augmentation to overcome these bottlenecks. Specifically, to enhance Identifiability, we provide the reward model with full reference solutions as context, enabling fine-grained…

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…

Stance classification, the task of predicting the viewpoint of an author on a subject of interest, has long been a focal point of research in domains ranging from social science to machine learning. Current stance detection methods rely…