Framing Matters: Addressing Framing Sensitivity in Decision-Making through Behaviorally-Grounded Value Alignment

Large Language Models (LLMs) are increasingly deployed in high-stakes decision-making settings such as legal reasoning, where consistency under factually equivalent inputs is critical. However, we find that fact-preserved but differently framed inputs can significantly destabilize LLM decisions. To systematically investigate this problem, we introduce Fragile, a large-scale benchmark that isolates fact-preserving semantic framing across three controlled dimensions: value-tinted narration, temporal slice, and narrative vividness. Our experiments reveal a high susceptibility of LLMs to framing, with an average decision flip rate of 28.6%. We find that simple prior prompt-level and activation-level interventions not only fail to suppress framing sensitivity but actively amplify it. We therefore propose Valign, a representation-level method that explicitly targets these framing dimensions by anchoring decisions to a stable value prior, steering hidden states toward the model's value-consistent direction, and projecting out temporal-vividness-sensitive directions from the model's hidden states. Valign consistently reduces framing-induced decision flips, demonstrating that robust mitigation requires directly targeting the internal pathways in which framing operates.

Enhancing Multilingual RAG Systems with Debiased Language Preference-Guided Query Fusion

Multilingual Retrieval-Augmented Generation (mRAG) systems often exhibit a perceived preference for high-resource languages, particularly English, resulting in the widespread adoption of English pivoting. While prior studies attribute this advantage to the superior English-centric capabilities of Large Language Models (LLMs), we find that such measurements are significantly distorted by structural priors inherent in evaluation benchmarks. Specifically, we identify exposure bias and a gold availability prior-both driven by the disproportionate concentration of resources in English-as well as cultural priors rooted in topic locality, as factors that hinder accurate assessment of genuine language preference. To address these biases, we propose DeLP (Debiased Language Preference), a calibrated metric designed to explicitly factor out these structural confounds. Our analysis using DeLP reveals that the previously reported English preference is largely a byproduct of evidence distribution rather than an inherent model bias. Instead, we find that retrievers fundamentally favor monolingual alignment between the query and the document language. Building on this insight, we introduce DELTA (DEbiased Language preference-guided Text Augmentation), a lightweight and efficient mRAG framework that strategically leverages monolingual alignment to optimize cross-lingual retrieval and generation. Experimental results demonstrate that DELTA consistently outperforms English pivoting and mRAG baselines across diverse languages.

Personality Editing for Language Models through Relevant Knowledge Editing

Large Language Models (LLMs) play a vital role in applications like conversational agents and content creation, where controlling a model's personality is crucial for maintaining tone, consistency, and engagement. However, traditional prompt-based techniques for controlling personality often fall short, as they do not effectively mitigate the model's inherent biases. In this paper, we introduce a novel method PALETTE that enhances personality control through knowledge editing. By generating adjustment queries inspired by psychological assessments, our approach systematically adjusts responses to personality-related queries similar to modifying factual knowledge, thereby achieving controlled shifts in personality traits. Experimental results from both automatic and human evaluations demonstrate that our method enables more stable and well-balanced personality control in LLMs.

Low-Resource Cross-Lingual Summarization through Few-Shot Learning with Large Language Models

Cross-lingual summarization (XLS) aims to generate a summary in a target language different from the source language document. While large language models (LLMs) have shown promising zero-shot XLS performance, their few-shot capabilities on this task remain unexplored, especially for low-resource languages with limited parallel data. In this paper, we investigate the few-shot XLS performance of various models, including Mistral-7B-Instruct-v0.2, GPT-3.5, and GPT-4. Our experiments demonstrate that few-shot learning significantly improves the XLS performance of LLMs, particularly GPT-3.5 and GPT-4, in low-resource settings. However, the open-source model Mistral-7B-Instruct-v0.2 struggles to adapt effectively to the XLS task with limited examples. Our findings highlight the potential of few-shot learning for improving XLS performance and the need for further research in designing LLM architectures and pre-training objectives tailored for this task. We provide a future work direction to explore more effective few-shot learning strategies and to investigate the transfer learning capabilities of LLMs for cross-lingual summarization.