相关论文: Surfacing Biases in Large Language Models using Co…

Although multimodal large language models (MLLMs) exhibit remarkable reasoning capabilities on complex multimodal understanding tasks, they still suffer from the notorious hallucination issue: generating outputs misaligned with obvious…

Weak-to-strong generalization provides a promising paradigm for scaling large language models (LLMs) by training stronger models on samples from aligned weaker ones, without requiring human feedback or explicit reward modeling. However, its…

Large Vision-Language Models (LVLMs) demonstrate significant progress in multimodal understanding and reasoning, yet object hallucination remains a critical challenge. While existing research focuses on mitigating language priors or…

Code generation aims to synthesize code and fulfill functional requirements based on natural language (NL) specifications, which can greatly improve development efficiency. In the era of large language models (LLMs), large code models…

When trained on large, unfiltered crawls from the internet, language models pick up and reproduce all kinds of undesirable biases that can be found in the data: they often generate racist, sexist, violent or otherwise toxic language. As…

Recent decoding methods improve the factuality of large language models (LLMs) by refining how the next token is selected during generation. These methods typically operate at the token level, leveraging internal representations to suppress…

Video language models (Video-LLMs) are prone to hallucinations, often generating plausible but ungrounded content when visual evidence is weak, ambiguous, or biased. Existing decoding methods, such as contrastive decoding (CD), rely on…

The use of Large Language Models (LLMs) for simulating user behavior in the domain of Interactive Information Retrieval has recently gained significant popularity. However, their application and capabilities remain highly debated and…

Large language Model (LLM)-assisted algorithm discovery is an iterative, black-box optimization process over programs to approximatively solve a target task, where an LLM proposes candidate programs and an external evaluator provides task…

Safety-aligned large language models (LLMs) often generate refusal responses to harmless queries due to the over-refusal problem. However, existing methods for mitigating over-refusal cannot maintain a low refusal ratio for harmless queries…

Large Language Models (LLMs) often generate hallucinations, producing outputs that are contextually inaccurate or factually incorrect. We introduce HICD, a novel method designed to induce hallucinations for contrastive decoding to mitigate…

It is evident that deep text classification models trained on human data could be biased. In particular, they produce biased outcomes for texts that explicitly include identity terms of certain demographic groups. We refer to this type of…

The rapid growth of Large Language Models (LLMs) usage has highlighted the importance of gradient-free in-context learning (ICL). However, interpreting their inner workings remains challenging. This paper introduces a novel multimodal…

Counterfactual explanations have emerged as a promising method for elucidating the behavior of opaque black-box models. Recently, several works leveraged pixel-space diffusion models for counterfactual generation. To handle noisy,…

Multimodal Large Language Models (MLLMs) have shown impressive perception and reasoning capabilities, yet they often suffer from hallucinations -- generating outputs that are linguistically coherent but inconsistent with the context of the…

Multilingual Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to perform knowledge-intensive tasks in multilingual settings by leveraging retrieved documents as external evidence. However, when the retrieved…

We address a not-widely-recognized subset of exploratory search, where a user sets out on a typically long "search quest" for the perfect wedding dress, overlooked research topic, killer company idea, etc. The first few outputs of current…

One of the most striking findings in modern research on large language models (LLMs) is that scaling up compute during training leads to better results. However, less attention has been given to the benefits of scaling compute during…

Learning representations that generalize well to unknown downstream tasks is a central challenge in representation learning. Existing approaches such as contrastive learning, self-supervised masking, and denoising auto-encoders address this…

Although achieving promising performance, recent analyses show that current generative large language models (LLMs) may still capture dataset biases and utilize them for generation, leading to poor generalizability and harmfulness of LLMs.…