相关论文: The Alignment Tax: Response Homogenization in Alig…
We introduce a simple, yet novel entropy-based framework to drive token efficiency in large language models during reasoning tasks. Our approach uses Shannon entropy from token-level logprobs as a confidence signal to enable early stopping,…
Recent alignment studies commonly remove introductory boilerplate phrases from supervised fine-tuning (SFT) datasets. This work challenges that assumption. We hypothesize that safety- and reasoning-oriented prefix sentences serve as…
Verbal confidence elicitation is widely used to extract uncertainty estimates from LLMs. We tested whether seven instruction-tuned open-weight models (3-9B parameters, four families) produce verbalised confidence that meets minimal validity…
Reasoning models are evaluated on single-turn benchmarks but deployed in multi-turn dialogue, where users push back on correct answers. Under sustained adversarial pressure we find a previously undocumented failure mode: the…
Aligning large language models (LLMs) to human preferences is a crucial step in building helpful and safe AI tools, which usually involve training on supervised datasets. Popular algorithms such as Direct Preference Optimization (DPO) rely…
As instruction-tuned large language models (LLMs) evolve, aligning pretrained foundation models presents increasing challenges. Existing alignment strategies, which typically leverage diverse and high-quality data sources, often overlook…
Reinforcement Learning from Human Feedback (RLHF) has been credited as the key advance that has allowed Large Language Models (LLMs) to effectively follow instructions and produce useful assistance. Classically, this involves generating…
Uncertainty quantification (UQ) has emerged as a promising approach for detecting hallucinations and low-quality output of Large Language Models (LLMs). However, obtaining proper uncertainty scores is complicated by the conditional…
Large language models (LLMs) have exhibited impressive zero-shot performance on inference tasks. However, LLMs may suffer from spurious correlations between input texts and output labels, which limits LLMs' ability to reason based purely on…
Large Language Models can generate synthetic survey responses at low cost, but their accuracy varies unpredictably across questions. We study the design problem of allocating a fixed budget of human respondents across estimation tasks when…
Modern large language models (LLMs) are often evaluated and deployed under a one-shot, greedy inference protocol, especially in professional settings that require deterministic behavior. This regime can systematically under-estimate a fixed…
Large language models (LLMs) exhibit strong generative capabilities but remain vulnerable to confabulations, fluent yet unreliable outputs that vary arbitrarily even under identical prompts. Leveraging a quantum tensor network based…
In this work, we explore uncertainty estimation as a proxy for correctness in LLM-generated code. To this end, we adapt two state-of-the-art techniques from natural language generation -- one based on entropy and another on mutual…
When annotators disagree on a label, the disagreement itself carries signal -- and the number of annotators needed to capture it depends on the evaluation metric. We fine-tune NLI models on label distributions subsampled from ChaosNLI, a…
Large Language Models (LLMs) are increasingly applied to complex tasks that require extended reasoning. In such settings, models often benefit from diverse chains-of-thought to arrive at multiple candidate solutions. This requires two…
We investigate the efficacy of Large Language Models (LLMs) in detecting implicit and explicit hate speech, examining how models with minimal safety alignment (uncensored) compare with more heavily aligned (censored) counterparts in a…
Hybrid Language Models (HLMs) combine the low-latency efficiency of Small Language Models (SLMs) on edge devices with the high accuracy of Large Language Models (LLMs) on centralized servers. Unlike traditional end-to-end LLM inference,…
We audit alignment-induced shifts in residual-stream activations of three open-weight instruction-tuned LLMs (Llama-3.1-8B-Instruct, Gemma-2-9B-it, Qwen-2.5-7B-Instruct) using the effective rank of the alignment modification matrix on…
Safety alignment mechanisms in large language models prevent responses to harmful queries through learned refusal behavior, yet these same mechanisms impede legitimate research applications including cognitive modeling, adversarial testing,…
Large Language Models (LLMs) are widely deployed in real-world applications, yet little is known about their training dynamics at the token level. Evaluation typically relies on aggregated training loss, measured at the batch level, which…