1 citations · 3 across the 10 of their papers we have counts for
13 papers
Pushback in a Haystack: Language Models Respond to Factual Errors Ambiguously and Ineffectively
Li Lucy, Myra Cheng, Svenja Guhr +7
The sycophancy of language models, or their failure to push back against faulty user input, is now widely studied. However, if LMs do push back, is sycophancy solved? We show that…
IDIOLEX: Unified and Continuous Representations for Idiolectal and Stylistic Variation
Anjali Kantharuban, Aarohi Srivastava, Fahim Faisal +5
Existing sentence representations primarily encode what a sentence says, rather than how it is expressed, even though the latter is important for many applications. In contrast, we…
BASS: Benchmarking Audio LMs for Musical Structure and Semantic Reasoning
Min Jang, Orevaoghene Ahia, Nazif Tamer +3
Music understanding is a complex task that often requires reasoning over both structural and semantic elements of audio. We introduce BASS, designed to evaluate music understanding…
Encode Once, Decode Never: Reusing Audio LM Internals for Efficient Temporal Localization
Joseph An, Phillip Keung, Jiaqi Wang +2
Audio language models process input audio into rich frame-level representations, but the standard approach to temporal localization generates timestamps as sequences of text tokens…
Cognitive Foundations for Reasoning and Their Manifestation in LLMs
Priyanka Kargupta, Shuyue Stella Li, Haocheng Wang +9
Large language models (LLMs) solve complex problems yet fail on simpler variants, suggesting they achieve correct outputs through mechanisms fundamentally different from human reas…
FLEXITOKENS: Flexible Tokenization for Evolving Language Models
Abraham Toluwase Owodunni, Orevaoghene Ahia, Sachin Kumar
Adapting language models to new data distributions by simple finetuning is challenging. This is due to the rigidity of their subword tokenizers, which typically remain unchanged du…
Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations
Brian Siyuan Zheng, Alisa Liu, Orevaoghene Ahia +3
Modern tokenizers employ deterministic algorithms to map text into a single "canonical" token sequence, yet the same string can be encoded as many non-canonical tokenizations using…
BLAB: Brutally Long Audio Bench
Orevaoghene Ahia, Martijn Bartelds, Kabir Ahuja +13
Developing large audio language models (LMs) capable of understanding diverse spoken interactions is essential for accommodating the multimodal nature of human communication and ca…
MAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization
Orevaoghene Ahia, Sachin Kumar, Hila Gonen +4
In multilingual settings, non-Latin scripts and low-resource languages are usually disadvantaged in terms of language models' utility, efficiency, and cost. Specifically, previous…
Voices Unheard: NLP Resources and Models for Yorùbá Regional Dialects
Orevaoghene Ahia, Anuoluwapo Aremu, Diana Abagyan +5
Yorùbá an African language with roughly 47 million speakers encompasses a continuum with several dialects. Recent efforts to develop NLP technologies for African languages have foc…
Critical Learning Periods: Leveraging Early Training Dynamics for Efficient Data Pruning
Everlyn Asiko Chimoto, Jay Gala, Orevaoghene Ahia +3
Neural Machine Translation models are extremely data and compute-hungry. However, not all data points contribute equally to model training and generalization. Data pruning to remov…
That was the last straw, we need more: Are Translation Systems Sensitive to Disambiguating Context?
Jaechan Lee, Alisa Liu, Orevaoghene Ahia +2
The translation of ambiguous text presents a challenge for translation systems, as it requires using the surrounding context to disambiguate the intended meaning as much as possibl…
AfriWOZ: Corpus for Exploiting Cross-Lingual Transferability for Generation of Dialogues in Low-Resource, African Languages
Tosin Adewumi, Mofetoluwa Adeyemi, Aremu Anuoluwapo +17
Dialogue generation is an important NLP task fraught with many challenges. The challenges become more daunting for low-resource African languages. To enable the creation of dialogu…