相关论文: Token-Level Entropy Reveals Demographic Disparitie…

Large Language Models (LLMs) are increasingly integrated into critical decision-making processes, such as loan approvals and visa applications, where inherent biases can lead to discriminatory outcomes. In this paper, we examine the nuanced…

This paper attempts a first analysis of citation distributions based on the genderedness of authors' first name. Following the extraction of first name and sex data from all human entity triplets contained in Wikidata, a first name…

Speech Large Language Models (SpeechLLMs) process spoken input directly, retaining cues such as accent and perceived gender that were previously removed in cascaded pipelines. This introduces speaker identity dependent variation in…

A common limitation of diagnostic tests for detecting social biases in NLP models is that they may only detect stereotypic associations that are pre-specified by the designer of the test. Since enumerating all possible problematic…

This paper argues that the relationship between lexical identity and prosody -- one well-studied parameter of linguistic variation -- can be characterized using information theory. We predict that languages that use prosody to make lexical…

We revisit the well-studied problem of estimating the Shannon entropy of a probability distribution, now given access to a probability-revealing conditional sampling oracle. In this model, the oracle takes as input the representation of a…

Despite recent successes in language models, their ability to represent numbers is insufficient. Humans conceptualize numbers based on their magnitudes, effectively projecting them on a number line; whereas subword tokenization fails to…

Your name tells a lot about you: your gender, ethnicity and so on. It has been shown that name embeddings are more effective in representing names than traditional substring features. However, our previous name embedding model is trained on…

Reasoning models often outperform smaller models but at 3--5$\times$ higher cost and added latency. We present entropy-guided refinement: a lightweight, test-time loop that uses token-level uncertainty to trigger a single, targeted…

Accurately matching visual and textual data in cross-modal retrieval has been widely studied in the multimedia community. To address these challenges posited by the heterogeneity gap and the semantic gap, we propose integrating Shannon…

We study how the Shannon entropy of sequences produced by an information source converges to the source's entropy rate. We synthesize several phenomenological approaches to applying information theoretic measures of randomness and memory to…

Unseen data conditions can inflict serious performance degradation on systems relying on supervised machine learning algorithms. Because data can often be unseen, and because traditional machine learning algorithms are trained in a…

As Large Language Models (LLMs) are increasingly used across different applications, concerns about their potential to amplify gender biases in various tasks are rising. Prior research has often probed gender bias using explicit gender cues…

We prove a lower estimate on the increase in entropy when two copies of a conditional random variable $X | Y$, with $X$ supported on $\mathbb{Z}_q=\{0,1,\dots,q-1\}$ for prime $q$, are summed modulo $q$. Specifically, given two i.i.d copies…

Instruction-tuned language models exhibit behavioural fairness in high-stakes decisions while retaining biased associations in their internal representations. However, whether these suppressed representations can affect model outputs - and…

Discrete speech representation learning has recently attracted increasing interest in both acoustic and semantic modeling. Existing approaches typically encode 16 kHz waveforms into discrete tokens at a rate of 25 or 50 tokens per second.…

Socio-demographic prompting (SDP) - prompting Large Language Models (LLMs) using demographic proxies to generate culturally aligned outputs - often shows LLM responses as stereotypical and biased. While effective in assessing LLMs' cultural…

In this paper, we report our discovery on named entity distribution in a general word embedding space, which helps an open definition on multilingual named entity definition rather than previous closed and constraint definition on named…

We present a study of the relationship between gender, linguistic style, and social networks, using a novel corpus of 14,000 Twitter users. Prior quantitative work on gender often treats this social variable as a female/male binary; we…

With widening deployments of natural language processing (NLP) in daily life, inherited social biases from NLP models have become more severe and problematic. Previous studies have shown that word embeddings trained on human-generated…