2 citations · 2 across the 9 of their papers we have counts for
6 papers · 1 filter
Test-Time Adaptation of Reasoning Strategies with Bayesian Nonparametric Memory
Keshav Ramji, Tahira Naseem, Ramón Fernandez Astudillo
While modern large language models (LLMs) have been trained to reason through verbalized chains-of-thought, the generation cost grows substantially due to suboptimal paths to reach…
Thinking Without Words: Efficient Latent Reasoning with Abstract Chain-of-Thought
Keshav Ramji, Tahira Naseem, Ramón Fernandez Astudillo
While long, explicit chains-of-thought (CoT) have proven effective on complex reasoning tasks, they are costly to generate during inference. Non-verbal reasoning methods have emerg…
Do LLMs Benefit From Their Own Words?
Jenny Y. Huang, Leshem Choshen, Wei Sun +5
In multi-turn conversations, large language models typically condition on the full conversation history: both past user prompts and assistant responses. We revisit this design choi…
Latent Principle Discovery for Language Model Self-Improvement
Keshav Ramji, Tahira Naseem, Ramón Fernandez Astudillo
When language model (LM) users aim to improve the quality of its generations, it is crucial to specify concrete behavioral attributes that the model should strive to reflect. Howev…
Multi-Document Grounded Multi-Turn Synthetic Dialog Generation
Young-Suk Lee, Chulaka Gunasekara, Danish Contractor +2
We introduce a technique for multi-document grounded multi-turn synthetic dialog generation that incorporates three main ideas. First, we control the overall dialog flow using taxo…
Self-Refinement of Language Models from External Proxy Metrics Feedback
Keshav Ramji, Young-Suk Lee, Ramón Fernandez Astudillo +5
It is often desirable for Large Language Models (LLMs) to capture multiple objectives when providing a response. In document-grounded response generation, for example, agent respon…