Baojun Min

Bingqing Song, Boran Han, Shuai Zhang et al. · amazon-science

Having an LLM that aligns with human preferences is essential for accommodating individual needs, such as maintaining writing style or generating specific topics of interest. The majority of current alignment methods rely on fine-tuning or prompting, which can be either costly or difficult to control. Model steering algorithms, which modify the model output by constructing specific steering directions, are typically easy to implement and optimization-free. However, their capabilities are typically limited to steering the model into one of the two directions (i.e., bidirectional steering), and there has been no theoretical understanding to guarantee their performance. In this work, we propose a theoretical framework to understand and quantify the model steering methods. Inspired by the framework, we propose a confident direction steering method (CONFST) that steers LLMs via modifying their activations at inference time. More specifically, CONFST builds a confident direction that is closely aligned with users' preferences, and this direction is then added to the activations of the LLMs to effectively steer the model output. Our approach offers three key advantages over popular bidirectional model steering methods: 1) It is more powerful, since multiple (i.e. more than two) users' preferences can be aligned simultaneously; 2) It is simple to implement, since there is no need to determine which layer to add the steering vector to; 3) No explicit user instruction is required. We validate our method on GPT-2 XL (1.5B), Mistral (7B) and Gemma-it (9B) models for tasks that require shifting the output of LLMs across various topics and styles, achieving superior performance over competing methods.

Dyah Adila, Shuai Zhang, Boran Han et al. · amazon-science

The integration of contextual information has significantly enhanced the performance of large language models (LLMs) on knowledge-intensive tasks. However, existing methods often overlook a critical challenge: the credibility of context documents can vary widely, potentially leading to the propagation of unreliable information. In this paper, we introduce CrEst, a novel weakly supervised framework for assessing the credibility of context documents during LLM inference--without requiring manual annotations. Our approach is grounded in the insight that credible documents tend to exhibit higher semantic coherence with other credible documents, enabling automated credibility estimation through inter-document agreement. To incorporate credibility into LLM inference, we propose two integration strategies: a black-box approach for models without access to internal weights or activations, and a white-box method that directly modifies attention mechanisms. Extensive experiments across three model architectures and five datasets demonstrate that CrEst consistently outperforms strong baselines, achieving up to a 26.86% improvement in accuracy and a 3.49% increase in F1 score. Further analysis shows that CrEst maintains robust performance even under high-noise conditions.