9 papers
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…
The Surprising Effectiveness of Shared Memory in Looped Transformers
Giovanni Monea, Keshav Ramji, Yousef El-Kurdi +4
Looped Transformers apply the same layers several times per token, adding compute to improve quality without more parameters. Each recursion, however, writes its own key-value cach…
Learning to Predict Distributions over Weight Updates for Test-Time Adaptation
Azal Ahmad Khan, Keshav Ramji, Tahira Naseem +2
Hypernetworks have recently shown success in dynamically adapting the parameters of Large Language Models (LLMs) at runtime based on signals such as task descriptions or additional…
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…
Language Modeling with Learned Meta-Tokens
Alok N. Shah, Khush Gupta, Keshav Ramji +1
While modern Transformer-based language models (LMs) have achieved major success in multi-task generalization, they often struggle to capture long-range dependencies within their c…
Conformal Language Model Reasoning with Coherent Factuality
Maxon Rubin-Toles, Maya Gambhir, Keshav Ramji +2
Language models are increasingly being used in important decision pipelines, so ensuring the correctness of their outputs is crucial. Recent work has proposed evaluating the "factu…
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…
Inductive Linguistic Reasoning with Large Language Models
Raghav Ramji, Keshav Ramji
Evaluating large language models (LLMs) on their linguistic reasoning capabilities is an important task to understand the gaps in their skills that may surface during large-scale a…
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…