相关论文: Finding the Translation Switch: Discovering and Ex…

Large Language Models (LLMs) have shown remarkable capabilities in tool calling and tool usage, but suffer from hallucinations where they choose incorrect tools, provide malformed parameters and exhibit 'tool bypass' behavior by performing…

Sparse Autoencoders (SAEs) are a prominent tool in mechanistic interpretability (MI) for decomposing neural network activations into interpretable features. However, the aspiration to identify a canonical set of features is challenged by…

Despite rapid adoption and deployment of large language models (LLMs), the internal computations of these models remain opaque and poorly understood. In this work, we seek to understand how high-level human-interpretable features are…

Despite the state-of-the-art performance of Large Language Models (LLMs), these models often suffer from hallucinations, which can undermine their performance in critical applications. In this work, we propose SAFE, a novel method for…

Large Language Models (LLMs) are rapidly reshaping machine translation (MT), particularly by introducing instruction-following, in-context learning, and preference-based alignment into what has traditionally been a supervised…

Translation-tailored Large language models (LLMs) exhibit remarkable translation capabilities, even competing with supervised-trained commercial translation systems. However, off-target translation remains an unsolved problem, especially…

Large language models (LLMs) have shown impressive abilities in leveraging pretrained knowledge through prompting, but they often struggle with unseen tasks, particularly in data-scarce scenarios. While cross-task in-context learning offers…

Recent advances in Large Multimodal Models (LMMs) lead to significant breakthroughs in both academia and industry. One question that arises is how we, as humans, can understand their internal neural representations. This paper takes an…

This study investigates how Large Language Models (LLMs) leverage source and reference data in machine translation evaluation task, aiming to better understand the mechanisms behind their remarkable performance in this task. We design the…

Hallucinations in large language models (LLMs) have recently become a significant problem. A recent effort in this direction is a shared task at Semeval 2024 Task 6, SHROOM, a Shared-task on Hallucinations and Related Observable…

Recent studies in interpretability have explored the inner workings of transformer models trained on tasks across various domains, often discovering that these networks naturally develop highly structured representations. When such…

Large language models (LLMs) have become proficient at solving a wide variety of tasks, including those involving multi-modal inputs. In particular, instantiating an LLM (such as LLaMA) with a speech encoder and training it on paired data…

Understanding and interpreting the internal representations of large language models (LLMs) remains an open challenge. Patchscopes introduced a method for probing internal activations by patching them into new prompts, prompting models to…

As Large Language Models become integral to software development, with substantial portions of AI-suggested code entering production, understanding their internal correctness mechanisms becomes critical for safe deployment. We apply sparse…

Human bilinguals often use similar brain regions to process multiple languages, depending on when they learned their second language and their proficiency. In large language models (LLMs), how are multiple languages learned and encoded? In…

A central goal for mechanistic interpretability has been to identify the right units of analysis in large language models (LLMs) that causally explain their outputs. While early work focused on individual neurons, evidence that neurons…

Sparse autoencoders (SAEs) and transcoders have become important tools for machine learning interpretability. However, measuring how interpretable they are remains challenging, with weak consensus about which benchmarks to use. Most…

Large Language Models (LLMs) exhibit In-Context Learning (ICL), which enables the model to perform new tasks conditioning only on the examples provided in the context without updating the model's weights. While ICL offers fast adaptation…

Recent work has found that sparse autoencoders (SAEs) are an effective technique for unsupervised discovery of interpretable features in language models' (LMs) activations, by finding sparse, linear reconstructions of LM activations. We…

Large language models (LLMs) have demonstrated human-like abilities in language-based tasks. While language is a defining feature of human intelligence, it emerges from more fundamental neurophysical processes rather than constituting the…