5 papers
Do LLMs Really Need 10+ Thoughts for "Find the Time 1000 Days Later"? Towards Structural Understanding of LLM Overthinking
Xinliang Frederick Zhang, Anhad Mohananey, Alexandra Chronopoulou +5
Models employing long chain-of-thought (CoT) reasoning have shown superior performance on complex reasoning tasks. Yet, this capability introduces a critical and often overlooked i…
Multi-Turn Puzzles: Evaluating Interactive Reasoning and Strategic Dialogue in LLMs
Kartikeya Badola, Jonathan Simon, Arian Hosseini +7
Large language models (LLMs) excel at solving problems with clear and complete statements, but often struggle with nuanced environments or interactive tasks which are common in mos…
What Matters for Model Merging at Scale?
Prateek Yadav, Tu Vu, Jonathan Lai +4
Model merging aims to combine multiple expert models into a more capable single model, offering benefits such as reduced storage and serving costs, improved generalization, and sup…
Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention
Tsendsuren Munkhdalai, Manaal Faruqui, Siddharth Gopal
This work introduces an efficient method to scale Transformer-based Large Language Models (LLMs) to infinitely long inputs with bounded memory and computation. A key component in o…
Deferred NAM: Low-latency Top-K Context Injection via Deferred Context Encoding for Non-Streaming ASR
Zelin Wu, Gan Song, Christopher Li +9
Contextual biasing enables speech recognizers to transcribe important phrases in the speaker's context, such as contact names, even if they are rare in, or absent from, the trainin…