Related papers: The Realignment Problem: When Right becomes Wrong …
Retrieval-augmented large language models, when optimized with outcome-level rewards, can achieve strong answer accuracy on multi-hop questions. However, under noisy retrieval, models frequently suffer from "right-answer-wrong-reason…
Understanding when and how linguistic knowledge emerges during language model training remains a central challenge for interpretability. Most existing tools are post hoc, rely on scalar metrics, or require nontrivial integration effort,…
Modern transformer models exhibit phase transitions during training, distinct shifts from memorisation to abstraction, but the mechanisms underlying these transitions remain poorly understood. Prior work has often focused on endpoint…
Recent advancements in Large Language Models (LLMs) have expanded the horizons of natural language understanding and generation. Notably, the output control and alignment with the input of LLMs can be refined through instruction tuning.…
Large language models (LLMs) remain unreliable for global enterprise applications due to substantial performance gaps between high-resource and mid/low-resource languages, driven by English-centric pretraining and internal reasoning biases.…
The rapid progress in Large Language Models (LLMs) poses potential risks such as generating unethical content. Assessing LLMs' values can help expose their misalignment, but relies on reference-free evaluators, e.g., fine-tuned LLMs or…
Reinforcement learning from human feedback (RLHF) is a crucial technique in aligning large language models (LLMs) with human preferences, ensuring these LLMs behave in beneficial and comprehensible ways to users. However, a longstanding…
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…
Aligning large language models (LLMs) with human values is a vital task for LLM practitioners. Current alignment techniques have several limitations: (1) requiring a large amount of annotated data; (2) demanding heavy human involvement; (3)…
Large Language Models (LLMs) have showcased impressive performance. However, due to their inability to capture relationships among samples, these frozen LLMs inevitably keep repeating similar mistakes. In this work, we propose our…
Personality manipulation in large language models (LLMs) is increasingly applied in customer service and agentic scenarios, yet its mechanisms and trade-offs remain unclear. We present a systematic study of personality control using the Big…
Despite the fact that offline methods for Large Language Models (LLMs) alignment do not require a direct reward model, they remain susceptible to overoptimization. This issue arises when the trained model deviates excessively from the…
Recommender systems (RS) have become essential tools for helping users efficiently navigate the overwhelming amount of information on e-commerce and social platforms. However, traditional RS relying on Collaborative Filtering (CF) struggles…
Human preference alignment is essential to improve the interaction quality of large language models (LLMs). Existing alignment methods depend on manually annotated preference data to guide the LLM optimization directions. However,…
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…
Previous work adopts large language models (LLMs) as evaluators to evaluate natural language process (NLP) tasks. However, certain shortcomings, e.g., fairness, scope, and accuracy, persist for current LLM evaluators. To analyze whether…
Post-training (via supervised fine-tuning) improves instruction-following, but often induces semantic mode collapse by biasing models toward low-entropy fine-tuning data at the expense of the high-entropy pretraining distribution.…
Large Language Models (LLMs) have shown superior performance in various applications and fields. To achieve better performance on specialized domains such as law and advertisement, LLMs are often continue pre-trained on in-domain data.…
Large language models (LLMs) have become integral to modern software development, enabling automated code generation at scale. However, validating the correctness of LLM-generated code remains a critical and largely unsolved challenge.…
Recent advancements in large language models (LLMs) have significantly enhanced the ability of LLM-based systems to perform complex tasks through natural language processing and tool interaction. However, optimizing these LLM-based systems…