8 papers
Parallel Token Prediction for Language Models
Felix Draxler, Justus Will, Farrin Marouf Sofian +3
Autoregressive decoding in language models is inherently slow, generating only one token per forward pass. We propose Parallel Token Prediction (PTP), a general-purpose framework f…
Lost in Simulation: LLM-Simulated Users are Unreliable Proxies for Human Users in Agentic Evaluations
Preethi Seshadri, Samuel Cahyawijaya, Ayomide Odumakinde +2
Agentic benchmarks increasingly rely on LLM-simulated users to scalably evaluate agent performance, yet the robustness, validity, and fairness of this approach remain unexamined. T…
Entropy-Aligned Decoding of LMs for Better Writing and Reasoning
Kareem Ahmed, Sameer Singh
Language models (LMs) are trained on billions of tokens in an attempt to recover the true language distribution. Still, vanilla random sampling from LMs yields low quality generati…
Characterizing Mamba's Selective Memory using Auto-Encoders
Tamanna Hossain, Robert L. Logan, Ganesh Jagadeesan +3
State space models (SSMs) are a promising alternative to transformers for language modeling because they use fixed memory during inference. However, this fixed memory usage require…
Leveraging In-Context Learning for Language Model Agents
Shivanshu Gupta, Sameer Singh, Ashish Sabharwal +2
In-context learning (ICL) with dynamically selected demonstrations combines the flexibility of prompting large language models (LLMs) with the ability to leverage training data to…
Nudging: Inference-time Alignment of LLMs via Guided Decoding
Yu Fei, Yasaman Razeghi, Sameer Singh
Large language models (LLMs) require alignment to effectively and safely follow user instructions. This process necessitates training an aligned version for every base model, resul…