Related papers: Working Notes on Late Interaction Dynamics: Analyz…

Reward models are central to large language model (LLM) post-training. However, past work has shown that they can reward spurious or undesirable attributes such as length, format, hallucinations, and sycophancy. In this work, we introduce…

Language and vision-language models have shown impressive performance across a wide range of tasks, but their internal mechanisms remain only partly understood. In this work, we study how individual attention heads in text-generative models…

Inverse Ising inference allows pairwise interactions of complex binary systems to be reconstructed from empirical correlations. Typical estimators used for this inference, such as Pseudo-likelihood maximization (PLM), are biased. Using the…

Recent literature has suggested the potential of using large language models (LLMs) to make classifications for tabular tasks. However, LLMs have been shown to exhibit harmful social biases that reflect the stereotypes and inequalities…

Last few years have seen unprecedented advances in capabilities of Large Language Models (LLMs). These advancements promise to benefit a vast array of application domains. However, due to their immense size, performing inference with LLMs…

Recently multimodal transformer models have gained popularity because their performance on language and vision tasks suggest they learn rich visual-linguistic representations. Focusing on zero-shot image retrieval tasks, we study three…

An important problem in the field of bioinformatics is to identify interactive effects among profiled variables for outcome prediction. In this paper, a logistic regression model with pairwise interactions among a set of binary covariates…

In bandit settings, optimizing long-term regret metrics requires exploration, which corresponds to sometimes taking myopically sub-optimal actions. When a long-lived principal merely recommends actions to be executed by a sequence of…

Large language models (LLMs) often fail to scale their performance on long-context tasks performance in line with the context lengths they support. This gap is commonly attributed to retrieval failures -- the models' inability to identify…

The alignment of Large Language Models (LLMs) for multi-turn conversations typically relies on reward signals derived from the content of the text. This approach, however, overlooks a rich, complementary source of signal: the dynamics of…

While biases in large language models (LLMs), such as stereotypes and cultural tendencies in outputs, have been examined and identified, their presence and characteristics in spoken dialogue models (SDMs) with audio input and output remain…

Large Audio-Language Models (LALMs) are enhanced with audio perception capabilities, enabling them to effectively process and understand multimodal inputs that combine audio and text. However, their performance in handling conflicting…

Sparse attention methods exploit the inherent sparsity in attention to speed up the prefilling phase of long-context inference, mitigating the quadratic complexity of full attention computation. While existing sparse attention methods rely…

As large language models (LLMs) become more integrated into societal systems, the risk of them perpetuating and amplifying harmful biases becomes a critical safety concern. Traditional methods for mitigating bias often rely on data…

Large language models are increasingly deployed across diverse applications. This often includes tasks LLMs have not encountered during training. This implies that enumerating and obtaining the high-quality training data for all tasks is…

Identifying relevant text spans is important for several downstream tasks in NLP, as it contributes to model explainability. While most span identification approaches rely on relatively smaller pre-trained language models like BERT, a few…

Algorithms deployed in education can shape the learning experience and success of a student. It is therefore important to understand whether and how such algorithms might create inequalities or amplify existing biases. In this paper, we…

Large Vision Language Models (LVLMs) have achieved remarkable progress in multimodal tasks, yet they also exhibit notable social biases. These biases often manifest as unintended associations between neutral concepts and sensitive human…

Large Language Models (LLMs) are increasingly deployed in high-stakes decision-making contexts. While prior work has shown that LLMs exhibit cognitive biases behaviorally, whether these biases correspond to identifiable internal…

Time-inconsistency is a characteristic of human behavior in which people plan for long-term benefits but take actions that differ from the plan due to conflicts with short-term benefits. Such time-inconsistent behavior is believed to be…