Recently, large language models (LLMs) have attracted considerable attention due to their
remarkable capabilities. However, LLMs' generation of biased or hallucinatory content …

Chain-of-thought prompting (CoT) advances the reasoning abilities of large language
models (LLMs) and achieves superior performance in arithmetic, commonsense, and …

Large Language Models (LLMs) have demonstrated remarkable success across various
domains. However, despite their promising performance in numerous real-world …

Recent research has shown that large-scale pretrained language models, specifically
transformers, tend to exhibit issues relating to racism, sexism, religion bias, and toxicity in …

With the rapid advancements of large language models (LLMs), information retrieval (IR)
systems, such as search engines and recommender systems, have undergone a significant …

A bstr act E xisti ng bias miti gati on met ho ds re q uire s ocialgr ou ps peci fic w or d pairs
(eg,“ma n”–“wo ma n”) f or eac hs ocial attri b ute (eg, ge nder), restricti ngt he bias miti gati …

Data visualization in the form of charts plays a pivotal role in data analysis, offering critical
insights and aiding in informed decision-making. Automatic chart understanding has …

Norm discovery is important for understanding and reasoning about the acceptable
behaviors and potential violations in human communication and interactions. We introduce …

Abstract Language models (LMs) automatically learn word embeddings during pre-training
on language corpora. Although word embeddings are usually interpreted as feature vectors …

Hallucination is often regarded as a major impediment for using large language models
(LLMs), especially for knowledge-intensive tasks. Even when the training corpus consists …