相关论文: Testing the Limits of Truth Directions in LLMs

Large language models (LLMs) have been shown to possess impressive capabilities, while also raising crucial concerns about the faithfulness of their responses. A primary issue arising in this context is the management of (un)answerable…

Large Language Models (LLMs) are increasingly used as powerful tools for several high-stakes natural language processing (NLP) applications. Recent prompting works claim to elicit intermediate reasoning steps and key tokens that serve as…

Advances in the general capabilities of large language models (LLMs) have led to their use for information retrieval, and as components in automated decision systems. A faithful representation of probabilistic reasoning in these models may…

Large language models (LLMs) are a promising venue for natural language understanding and generation tasks. However, current LLMs are far from reliable: they are prone to generate non-factual information and, more crucially, to contradict…

Large language models (LLMs) are capable of generating plausible explanations of how they arrived at an answer to a question. However, these explanations can misrepresent the model's "reasoning" process, i.e., they can be unfaithful. This,…

Large Language Models (LLMs) have made significant advances in natural language processing, but their underlying mechanisms are often misunderstood. Despite exhibiting coherent answers and apparent reasoning behaviors, LLMs rely on…

Previous work has showcased the intriguing capability of large language models (LLMs) in retrieving facts and processing context knowledge. However, only limited research exists on the layer-wise capability of LLMs to encode knowledge,…

Despite the effectiveness of large language models (LLMs) for code generation, they often output incorrect code. One reason is that model output probabilities are often not well-correlated with correctness, and reflect only the final output…

Large Language Models (LLMs), trained on extensive web-scale corpora, have demonstrated remarkable abilities across diverse tasks, especially as they are scaled up. Nevertheless, even state-of-the-art models struggle in certain cases,…

Efforts to apply transformer-based language models (TLMs) to the problem of reasoning in natural language have enjoyed ever-increasing success in recent years. The most fundamental task in this area to which nearly all others can be reduced…

Large Language Models (LLMs) often encode whether a statement is true as a vector in their residual stream activations. These vectors, also known as truth vectors, have been studied in prior work, however how they change when context is…

Quantization enables efficient deployment of large language models (LLMs) in resource-constrained environments by significantly reducing memory and computation costs. While quantized LLMs often maintain performance on perplexity and…

Instruction-tuned Large Language Models (LLMs) can perform a wide range of tasks given natural language instructions to do so, but they are sensitive to how such instructions are phrased. This issue is especially concerning in healthcare,…

Fine-tuning pre-trained large language models (LLMs) on a diverse array of tasks has become a common approach for building models that can solve various natural language processing (NLP) tasks. However, where and to what extent these models…

Decoding methods play an indispensable role in converting language models from next-token predictors into practical task solvers. Prior research on decoding methods, primarily focusing on task-specific models, may not extend to the current…

Large language models (LLMs) tend to follow maliciously crafted instructions to generate deceptive responses, posing safety challenges. How deceptive instructions alter the internal representations of LLM compared to truthful ones remains…

Large Language Models (LLMs) have been shown to achieve breakthrough performance on complex logical reasoning tasks. Nevertheless, most existing research focuses on employing formal language to guide LLMs to derive reliable reasoning paths,…

Large language models (LLMs) are the result of a massive experiment in bottom-up, data-driven reverse engineering of language at scale. Despite their utility in a number of downstream NLP tasks, ample research has shown that LLMs are…

Instruction tuning -- fine-tuning a large language model (LLM) on pairs of instructions and desired outcomes -- is an approach that enables pre-trained language models to perform real-world tasks and follow human instructions. Its practical…

We posit that large language models (LLMs) should be capable of expressing their intrinsic uncertainty in natural language. For example, if the LLM is equally likely to output two contradicting answers to the same question, then its…