Related papers: CM-Align: Consistency-based Multilingual Alignment…
Large language models (LLMs) have demonstrated impressive performance on a number of natural language processing tasks, such as question answering and text summarization. However, their performance on sequence labeling tasks such as intent…
A key requirement in developing Generative Language Models (GLMs) is to have their values aligned with human values. Preference-based alignment is a widely used paradigm for this purpose, in which preferences over generation pairs are first…
Large Language Models (LLMs) have demonstrated promising capabilities as automatic evaluators in assessing the quality of generated natural language. However, LLMs still exhibit biases in evaluation and often struggle to generate coherent…
Extending large language models to effectively handle long contexts requires instruction fine-tuning on input sequences of similar length. To address this, we present LongAlign -- a recipe of the instruction data, training, and evaluation…
Human feedback plays a pivotal role in aligning large language models (LLMs) with human preferences. However, such feedback is often noisy or inconsistent, which can degrade the quality of reward models and hinder alignment. While various…
Large Language Models (LLMs) have been adopted and deployed worldwide for a broad variety of applications. However, ensuring their safe use remains a significant challenge. Preference training and safety measures often overfit to harms…
As large language models (LLMs) are deployed in high-stakes domains like healthcare, understanding how well their decision-making aligns with human preferences and values becomes crucial, especially when we recognize that there is no single…
It is known that large language models (LLMs) underperform in English dialects, and that improving them is difficult due to data scarcity. In this work we investigate how quality and availability impact the feasibility of improving LLMs in…
This paper addresses the challenges of aligning large language models (LLMs) with human values via preference learning (PL), focusing on incomplete and corrupted data in preference datasets. We propose a novel method for robustly and…
Applying large language models (LLMs) to assist in psycho-counseling is an emerging and meaningful approach, driven by the significant gap between patient needs and the availability of mental health support. However, current LLMs struggle…
Based on the foundation of Large Language Models (LLMs), Multilingual LLMs (MLLMs) have been developed to address the challenges faced in multilingual natural language processing, hoping to achieve knowledge transfer from high-resource…
Dataset curation has become a basis for strong large language model (LLM) performance. While various rule-based filtering heuristics exist for English and multilingual datasets, model-based filtering techniques have primarily focused on…
Large language models (LLMs) can answer prompts in many languages, despite being trained predominantly on English; yet, the mechanisms driving this generalization remain poorly understood. This work asks: How does an LLM's ability to align…
Multilingual language models (LMs) promise broader NLP access, yet current systems deliver uneven performance across the world's languages. This survey examines why these gaps persist and whether they reflect intrinsic linguistic difficulty…
Large language models~(LLMs) are expected to be helpful, harmless, and honest. In different alignment scenarios, such as safety, confidence, and general preference alignment, binary preference data collection and reward modeling are…
Direct Preference Optimization (DPO) and its variants have become the de facto standards for aligning large language models (LLMs) with human preferences or specific goals. However, DPO requires high-quality preference data and suffers from…
The prevailing approach to aligning Large Language Models (LLMs) typically relies on human or AI feedback and assumes access to specific types of preference datasets. In our work, we question the efficacy of such datasets and explore…
Large Reasoning Models (LRMs) still exhibit large performance gaps between English and other languages, yet much current work assumes these gaps can be closed simply by making reasoning in every language resemble English reasoning. This…
Although humans inherently have diverse values, current large language model (LLM) alignment methods often assume that aligning LLMs with the general public's preferences is optimal. A major challenge in adopting a more individualized…
In recent research on large language models (LLMs), there has been a growing emphasis on aligning these models with human values to reduce the impact of harmful content. However, current alignment methods often rely solely on singular forms…