Related papers: Counterfactual Token Generation in Large Language …
Natural language explanations of deep neural network decisions provide an intuitive way for a AI agent to articulate a reasoning process. Current textual explanations learn to discuss class discriminative features in an image. However, it…
Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in aligning visual inputs with natural language outputs. Yet, the extent to which generated tokens depend on visual modalities remains poorly understood,…
Multimodal large language models (MLLMs) carry the potential to support humans in processing vast amounts of information. While MLLMs are already being used as a fact-checking tool, their abilities and limitations in this regard are…
Large language models such as GPT and Llama are trained with a next-token prediction loss. In this work, we suggest that training language models to predict multiple future tokens at once results in higher sample efficiency. More…
As large language models have shown remarkable capabilities in conversing via natural language, the question arises as to how LLMs could potentially assist chemical engineers in research and industry with domain-specific tasks. We generate…
Story generation aims to automatically produce coherent, structured, and engaging narratives. Although large language models (LLMs) have significantly advanced text generation, stories generated by LLMs still diverge from human-authored…
Large Language Models (LLMs) have been shown to generate harmful content. However, the underlying causes of such behavior remain under explored. We propose a causal mediation analysis-based approach to identify the causal factors…
Causality is essential for understanding complex systems, such as the economy, the brain, and the climate. Constructing causal graphs often relies on either data-driven or expert-driven approaches, both fraught with challenges. The former…
Large Language Models (LLMs) are increasingly used as code assistants, yet their behavior when explicitly asked to generate insecure code remains poorly understood. While prior research has focused on unintended vulnerabilities, this study…
Causal reasoning capability is critical in advancing large language models (LLMs) toward strong artificial intelligence. While versatile LLMs appear to have demonstrated capabilities in understanding contextual causality and providing…
Story generation, namely generating a reasonable story from a leading context, is an important but challenging task. In spite of the success in modeling fluency and local coherence, existing neural language generation models (e.g., GPT-2)…
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…
One of the key tasks in machine learning for tabular data is feature engineering. Although it is vital for improving the performance of models, it demands considerable human expertise and deep domain knowledge, making it labor-intensive…
Standard classification models often map inputs directly to labels without explicit reasoning, potentially limiting their performance, robustness, and interpretability. This paper introduces a novel two-stage approach to enhance text…
Chain-of-thought explanations are widely used to inspect the decision process of large language models (LLMs) and to evaluate the trustworthiness of model outputs, making them important for effective collaboration between LLMs and humans.…
Recovering the structure of causal graphical models from observational data is an essential yet challenging task for causal discovery in scientific scenarios. Domain-specific causal discovery usually relies on expert validation or prior…
Safe deployment of large language models (LLMs) may benefit from a reliable method for assessing their generated content to determine when to abstain or to selectively generate. While likelihood-based metrics such as perplexity are widely…
Large language models (LLMs) can solve problems step-by-step. While this chain-of-thought (CoT) reasoning boosts LLMs' performance, it is unclear if LLMs \textit{know} when to use CoT and whether those CoT are always necessary to answer the…
We introduce the concept of the self-referencing causal cycle (abbreviated RECALL) - a mechanism that enables large language models (LLMs) to bypass the limitations of unidirectional causality, which underlies a phenomenon known as the…
Recent generative models have demonstrated impressive capabilities in generating realistic and visually pleasing images grounded on textual prompts. Nevertheless, a significant challenge remains in applying these models for the more…