9 papers
Fairness Beyond a Single Run: Training-Seed Variability in Speech LLM Adaptation
Srishti Ginjala, Eric Fosler-Lussier, Srinivasan Parthasarathy
Demographic fairness gaps in automatic speech recognition are almost always reported from a single training run. We fine-tune the Q-former projector and LoRA adapters of a speech L…
Diagnosing the Sources of Compositional Failure in Vision-Language Models: A Controlled Analysis
Mona Gandhi, Cenk Merih Olcay, Kuan-Chieh Lo +3
Vision-language models (VLMs) often struggle with compositional reasoning tasks, but the reasons for this underperformance remain unclear. A common hypothesis is that models strugg…
Temporal Taxation Compounds Under Post-Training Compression of Whisper Models
Srishti Ginjala, Eric Fosler-Lussier, Christopher W. Myers +1
Automatic speech recognition models are audited for demographic fairness at full precision, yet the models that ship to production have been quantized, pruned, and distilled. We as…
Through the PRISM: Principle-Aware, Interpretable, and Multi-Scale Evaluation of Visual Designs
Mona Gandhi, KJ Joseph, Srinivasan Parthasarathy +1
Effective visual communication stems from the harmony of multiple design principles, such as readability, contrast, alignment, overlap, and coherence, which collectively govern cla…
AffectCodec: Emotion-Preserving Neural Speech Codec for Expressive Speech Modeling
Jiacheng Shi, Hongfei Du, Xinyuan Song +3
Neural speech codecs provide discrete representations for speech language models, but emotional cues are often degraded during quantization. Existing codecs mainly optimize acousti…
Do LLM Decoders Listen Fairly? Benchmarking How Language Model Priors Shape Bias in Speech Recognition
Srishti Ginjala, Eric Fosler-Lussier, Christopher W. Myers +1
As pretrained large language models replace task-specific decoders in speech recognition, a critical question arises: do their text-derived priors make recognition fairer or more b…
Loop, Think, & Generalize: Implicit Reasoning in Recurrent-Depth Transformers
Harsh Kohli, Srinivasan Parthasarathy, Huan Sun +1
We study implicit reasoning, i.e. the ability to combine knowledge or rules within a single forward pass. While transformer-based large language models store substantial factual kn…
Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive Domains
Yash Saxena, Ankur Padia, Mandar S Chaudhary +3
Retrieval-Augmented Generation (RAG) systems deployed in sensitive domains must provide interpretable evidence selection and robust safeguards against data poisoning, yet current a…
From Guessing to Asking: An Approach to Resolving the Persona Knowledge Gap in LLMs during Multi-Turn Conversations
Sarvesh Baskar, Tanmay Tulsidas Verelakar, Srinivasan Parthasarathy +1
In multi-turn dialogues, large language models (LLM) face a critical challenge of ensuring coherence while adapting to user-specific information. This study introduces the persona…