Related papers: Notation-level confounding: When inconsistent mole…

Molecule discovery is a pivotal research field, impacting everything from medicine to materials. Recently, Large Language Models (LLMs) have been widely adopted in molecular understanding and generation, serving as a bridge between the…

Code-mixed languages, characterized by frequent within-sentence language transitions, present structural challenges that standard language models fail to address. In this work, we propose CMLFormer, an enhanced multi-layer dual-decoder…

Large Language Models (LLMs) have significantly transformed our daily life and established a new paradigm in natural language processing (NLP). However, the predominant pretraining of LLMs on extensive web-based texts remains insufficient…

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…

Large language models (LLMs) exhibit failures on elementary symbolic tasks such as character counting in a word, despite excelling on complex benchmarks. Although this limitation has been noted, the internal reasons remain unclear. We use…

Evaluating whether vision-language models (VLMs) reason consistently across representations is challenging because modality comparisons are typically confounded by task differences and asymmetric information. We introduce SEAM, a benchmark…

Large language models (LLMs), endowed with exceptional reasoning capabilities, are adept at discerning profound user interests from historical behaviors, thereby presenting a promising avenue for the advancement of recommendation systems.…

ML models have errors when used for predictions. The errors are unknown but can be quantified by model uncertainty. When multiple ML models are trained using the same training points, their model uncertainties may be statistically…

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

Pretrained language model (PLM) hidden states are frequently employed as contextual word embeddings (CWE): high-dimensional representations that encode semantic information given linguistic context. Across many areas of computational…

In this paper we motivate the causal mechanisms behind sample selection induced collider bias (selection collider bias) that can cause Large Language Models (LLMs) to learn unconditional dependence between entities that are unconditionally…

Large language models (LLMs) take sequences of subwords as input, requiring them to effective compose subword representations into meaningful word-level representations. In this paper, we present a comprehensive set of experiments to probe…

Multilingual language models (MLLMs) have demonstrated remarkable abilities to transfer knowledge across languages, despite being trained without explicit cross-lingual supervision. We analyze the parameter spaces of three MLLMs to study…

Color serves as a fundamental dimension of human visual perception and a primary means of communicating about objects and scenes. As vision-language models (VLMs) become increasingly prevalent, understanding whether they name colors like…

Recent years have witnessed a significant increase in the performance of Vision and Language tasks. Foundational Vision-Language Models (VLMs), such as CLIP, have been leveraged in multiple settings and demonstrated remarkable performance…

Machine learning has transformed material discovery for inorganic compounds and small molecules, yet polymers remain largely inaccessible to these methods. While data scarcity is often cited as the primary bottleneck, we demonstrate that…

Protein language models (PLMs) encode rich biological information, yet their internal neuron representations are poorly understood. We introduce the first automated framework for labeling every neuron in a PLM with biologically grounded…

Compositional generalization benchmarks for semantic parsing seek to assess whether models can accurately compute meanings for novel sentences, but operationalize this in terms of logical form (LF) prediction. This raises the concern that…

Scientific language models drive research innovation but require extensive fine-tuning on large datasets. This work enhances such models by improving their inference and evaluation capabilities with minimal or no additional training.…

Language Models (LMs) have shown promising performance in natural language generation. However, as LMs often generate incorrect or hallucinated responses, it is crucial to correctly quantify their uncertainty in responding to given inputs.…