103 citations · 330 across the 70 of their papers we have counts for
26 papers · 1 filter
The Role of Disfluencies in Speech Translation
Maike Züfle, Maria Teleki, Fabian Retkowski +5
Current speech translation systems, including SpeechLLMs, are trained on cleaned text and tend to strip disfluencies like filled pauses and false starts rather than translate them.…
Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation
Xingyu Su, Jacob Helwig, Shubham Parashar +6
We study the transformation of autoregressive models (ARLMs) into diffusion language models (DLMs). Rather than pretraining from scratch, prior work replaces the causal attention i…
DisasterBench: Benchmarking LLM Planning under Typed Tool Interface Constraints
Zhitong Chen, Kai Yin, Weifeng Zhang +7
Disasters cause severe societal impacts, demanding rapid coordination of heterogeneous AI tools, from satellite analysis to flood prediction and damage assessment, into coherent mu…
Learnability-Informed Fine-Tuning of Diffusion Language Models
Shubham Parashar, Atharv Chagi, Jacob Helwig +5
We aim to improve the reasoning capabilities of diffusion language models (DLMs). While SFT is a popular post-training recipe for autoregressive models, its use in DLMs faces chall…
Beyond Single Ground Truth: Reference Monism as Epistemic Injustice in ASR Evaluation
Anna Seo Gyeong Choi, Maria Teleki, James Caverlee +3
Automatic speech recognition (ASR) evaluation compares system output to ground truth transcripts, with Word Error Rate (WER) quantifying the distance between them. But ground truth…
DisastQA: A Comprehensive Benchmark for Evaluating Question Answering in Disaster Management
Zhitong Chen, Kai Yin, Xiangjue Dong +7
Accurate question answering (QA) in disaster management requires reasoning over uncertain and conflicting information, a setting poorly captured by existing benchmarks built on cle…
CHOIR: Collaborative Harmonization fOr Inference Robustness
Xiangjue Dong, Cong Wang, Maria Teleki +2
Persona-assigned Large Language Models (LLMs) can adopt diverse roles, enabling personalized and context-aware reasoning. However, even minor demographic perturbations in personas,…
Language Models as Semantic Augmenters for Sequential Recommenders
Mahsa Valizadeh, Xiangjue Dong, Rui Tuo +1
Large Language Models (LLMs) excel at capturing latent semantics and contextual relationships across diverse modalities. However, in modeling user behavior from sequential interact…
Z-Scores: A Metric for Linguistically Assessing Disfluency Removal
Maria Teleki, Sai Janjur, Haoran Liu +10
Evaluating disfluency removal in speech requires more than aggregate token-level scores. Traditional word-based metrics such as precision, recall, and F1 (E-Scores) capture overall…
Conversational Speech Reveals Structural Robustness Failures in SpeechLLM Backbones
Maria Teleki, Sai Janjur, Haoran Liu +11
LLMs serve as the backbone in SpeechLLMs, yet their behavior on spontaneous conversational input remains poorly understood. Conversational speech contains pervasive disfluencies --…
Masculine Defaults via Gendered Discourse in Podcasts and Large Language Models
Maria Teleki, Xiangjue Dong, Haoran Liu +1
Masculine defaults are widely recognized as a significant type of gender bias, but they are often unseen as they are under-researched. Masculine defaults involve three key parts: (…
GraphCheck: Breaking Long-Term Text Barriers with Extracted Knowledge Graph-Powered Fact-Checking
Yingjian Chen, Haoran Liu, Yinhong Liu +8
Large language models (LLMs) are widely used, but they often generate subtle factual errors, especially in long-form text. These errors are fatal in some specialized domains such a…
A Survey on LLM Inference-Time Self-Improvement
Xiangjue Dong, Maria Teleki, James Caverlee
Techniques that enhance inference through increased computation at test-time have recently gained attention. In this survey, we investigate the current state of LLM Inference-Time…
FANTAstic SEquences and Where to Find Them: Faithful and Efficient API Call Generation through State-tracked Constrained Decoding and Reranking
Zhuoer Wang, Leonardo F. R. Ribeiro, Alexandros Papangelis +6
API call generation is the cornerstone of large language models' tool-using ability that provides access to the larger world. However, existing supervised and in-context learning a…
KG-Rank: Enhancing Large Language Models for Medical QA with Knowledge Graphs and Ranking Techniques
Rui Yang, Haoran Liu, Edison Marrese-Taylor +8
Large language models (LLMs) have demonstrated impressive generative capabilities with the potential to innovate in medicine. However, the application of LLMs in real clinical sett…
Disclosure and Mitigation of Gender Bias in LLMs
Xiangjue Dong, Yibo Wang, Philip S. Yu +1
Large Language Models (LLMs) can generate biased responses. Yet previous direct probing techniques contain either gender mentions or predefined gender stereotypes, which are challe…
: A Distribution-Aware Adversarial Attack against Language Models
Yibo Wang, Xiangjue Dong, James Caverlee +1
Language models can be manipulated by adversarial attacks, which introduce subtle perturbations to input data. While recent attack methods can achieve a relatively high attack succ…
Probing Explicit and Implicit Gender Bias through LLM Conditional Text Generation
Xiangjue Dong, Yibo Wang, Philip S. Yu +1
Large Language Models (LLMs) can generate biased and toxic responses. Yet most prior work on LLM gender bias evaluation requires predefined gender-related phrases or gender stereot…
Unsupervised Candidate Answer Extraction through Differentiable Masker-Reconstructor Model
Zhuoer Wang, Yicheng Wang, Ziwei Zhu +1
Question generation is a widely used data augmentation approach with extensive applications, and extracting qualified candidate answers from context passages is a critical step for…
CoPT: Mitigating Bias in Pre-trained Language Models through Counterfactual Contrastive Prompt Tuning
Xiangjue Dong, Ziwei Zhu, Zhuoer Wang +2
Pre-trained Language Models are widely used in many important real-world applications. However, recent studies show that these models can encode social biases from large pre-traini…
PromptAttack: Probing Dialogue State Trackers with Adversarial Prompts
Xiangjue Dong, Yun He, Ziwei Zhu +1
A key component of modern conversational systems is the Dialogue State Tracker (or DST), which models a user's goals and needs. Toward building more robust and reliable DSTs, we in…
Closed-book Question Generation via Contrastive Learning
Xiangjue Dong, Jiaying Lu, Jianling Wang +1
Question Generation (QG) is a fundamental NLP task for many downstream applications. Recent studies on open-book QG, where supportive answer-context pairs are provided to models, h…
Identifying Hijacked Reviews
Monika Daryani, James Caverlee
Fake reviews and review manipulation are growing problems on online marketplaces globally. Review Hijacking is a new review manipulation tactic in which unethical sellers "hijack"…
Infusing Disease Knowledge into BERT for Health Question Answering, Medical Inference and Disease Name Recognition
Yun He, Ziwei Zhu, Yin Zhang +2
Knowledge of a disease includes information of various aspects of the disease, such as signs and symptoms, diagnosis and treatment. This disease knowledge is critical for many heal…