Newest Papers
Frustration, cautious optimism expressed by elected officials in wake of FWISD takeover | KERA News
https://www.keranews.org/cecilia-lenzen-the-texas-tribune, https://www.keranews.org/drew-shaw-fort-worth-report
KERA News·2025
Fort Worth’s local and state leaders said they want transparency and accountability as the state takes control of the school district.
No ratings yet
View paper →Efficient semantic uncertainty quantification in language models via diversity-steered sampling
Ji Won Park, Kyunghyun Cho
arXiv·2025
Accurately estimating semantic aleatoric and epistemic uncertainties in large language models (LLMs) is particularly challenging in free-form question answering (QA), where obtaining stable estimates often requires many expensive generations. We introduce a diversity-steered sampler that discourages semantically redundant outputs during decoding, covers both autoregressive and masked diffusion paradigms, and yields substantial sample-efficiency gains. The key idea is to inject a continuous semantic-similarity penalty into the model's proposal distribution using a natural language inference (NLI) model lightly finetuned on partial prefixes or intermediate diffusion states. We debias downstream uncertainty estimates with importance reweighting and shrink their variance with control variates. Across four QA benchmarks, our method matches or surpasses baselines while covering more semantic clusters with the same number of samples. Being modular and requiring no gradient access to the base LLM, the framework promises to serve as a drop-in enhancement for uncertainty estimation in risk-sensitive model deployments.
No ratings yet
View paper →Reducing the Probability of Undesirable Outputs in Language Models Using Probabilistic Inference
Stephen Zhao, Aidan Li, Rob Brekelmans, Roger Grosse
arXiv·2025
Reinforcement learning (RL) has become a predominant technique to align language models (LMs) with human preferences or promote outputs which are deemed to be desirable by a given reward function. Standard RL approaches optimize average reward, while methods explicitly focused on reducing the probability of undesired outputs typically come at a cost to average-case performance. To improve this tradeoff, we introduce RePULSe, a new training method that augments the standard RL loss with an additional loss that uses learned proposals to guide sampling low-reward outputs, and then reduces those outputs' probability. We run experiments demonstrating that RePULSe produces a better tradeoff of expected reward versus the probability of undesired outputs and is more adversarially robust, compared to standard RL alignment approaches and alternatives.
No ratings yet
View paper →