相关论文: The Hydra Effect: Emergent Self-repair in Language…

Transformer models have established new benchmarks in natural language processing; however, their increasing depth results in substantial growth in parameter counts. While existing recurrent transformer methods address this issue by…

The success of deep networks is crucially attributed to their ability to capture latent features within a representation space. In this work, we investigate whether the underlying learned features of a model can be efficiently retrieved…

We introduce Heptapod, an image autoregressive model that adheres to the foundational principles of language modeling. Heptapod employs \textbf{causal attention}, \textbf{eliminates reliance on CFG}, and \textbf{eschews the trend of…

Emergence is a fascinating property of large language models and neural networks more broadly: as models scale and train for longer, they sometimes develop new abilities in sudden ways. Despite initial studies, we still lack a comprehensive…

Large Vision-Language Models (LVLMs) have shown remarkable performance on many visual-language tasks. However, these models still suffer from multimodal hallucination, which means the generation of objects or content that violates the…

Answering multi-hop reasoning questions requires retrieving and synthesizing information from diverse sources. Language models (LMs) struggle to perform such reasoning consistently. We propose an approach to pinpoint and rectify multi-hop…

Large language models (LLMs) have transformed natural language processing, achieving remarkable performance across diverse tasks. However, their impressive fluency often comes at the cost of producing false or fabricated information, a…

Neural networks are among the state-of-the-art techniques for language modeling. Existing neural language models typically map discrete words to distributed, dense vector representations. After information processing of the preceding…

The iterated learning model is an agent model which simulates the transmission of of language from generation to generation. It is used to study how the language adapts to pressures imposed by transmission. In each iteration, a language…

As Large Language Models become more ubiquitous across domains, it becomes important to examine their inherent limitations critically. This work argues that hallucinations in language models are not just occasional errors but an inevitable…

Despite the remarkable performance of generative large language models (LLMs) on abstractive summarization, they face two significant challenges: their considerable size and tendency to hallucinate. Hallucinations are concerning because…

As Large Language Models (LLMs) continue to scale, post-training pruning has emerged as a promising approach to reduce computational costs while preserving performance. Existing methods such as SparseGPT and Wanda achieve high sparsity…

Vision-language models (VLMs) have recently shown remarkable capabilities in visual understanding and generation, but remain vulnerable to adversarial manipulations of visual content. Prior object-hiding attacks primarily rely on…

Persistent language-model agents increasingly combine tool use, tiered memory, reflective prompting, and runtime adaptation. In such systems, behavior is shaped not only by current prompts but by mutable internal conditions that influence…

Scaling up model depth and size is now a common approach to raise accuracy in many deep learning (DL) applications, as evidenced by the widespread success of multi-billion or even trillion parameter models in natural language processing…

According to the Language Familiarity Effect (LFE), people are better at discriminating between speakers of their native language. Although this cognitive effect was largely studied in the literature, experiments have only been conducted on…

Large Language Models (LLMs) are powerful linguistic engines but remain susceptible to hallucinations: plausible-sounding outputs that are factually incorrect or unsupported. In this work, we present a mathematically grounded framework to…

We investigate how large language models (LLMs) fail when tabular data in an otherwise canonical representation is subjected to semantic and structural distortions. Our findings reveal that LLMs lack an inherent ability to detect and…

The standard practice for training large language models involves packing multiple documents together to optimize computational efficiency. However, the impact of this process on the models' capabilities remains largely unexplored. To…

Recent advancements in large language models (LLMs) highlight their fluency in generating responses to diverse prompts. However, these models sometimes generate plausible yet incorrect ``hallucinated" facts, undermining trust. A frequent…