相关论文: Explaining Length Bias in LLM-Based Preference Eva…

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…

Self-Rewarding Language Models propose an architecture in which the Large Language Models(LLMs) both generates responses and evaluates its own outputs via LLM-as-a-Judge prompting, dynamically improving its generative capabilities through…

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…

Reinforcement Learning from Human Feedback (RLHF) has achieved considerable success in aligning large language models (LLMs) by modeling human preferences with a learnable reward model and employing a reinforcement learning algorithm to…

The conformity effect describes the tendency of individuals to align their responses with the majority. Studying this bias in large language models (LLMs) is crucial, as LLMs are increasingly used in various information-seeking and…

One of the most widely used tasks for evaluating Large Language Models (LLMs) is Multiple-Choice Question Answering (MCQA). While open-ended question answering tasks are more challenging to evaluate, MCQA tasks are, in principle, easier to…

Current large language models (LLMs) generally show a significant performance gap in alignment between English and other languages. To bridge this gap, existing research typically leverages the model's responses in English as a reference to…

The computational treatment of arguments on controversial issues has been subject to extensive NLP research, due to its envisioned impact on opinion formation, decision making, writing education, and the like. A critical task in any such…

The adoption of large language models (LLMs) is transforming the peer review process, from assisting reviewers in writing detailed evaluations to generating entire reviews automatically. While these capabilities offer new opportunities,…

Reward models (RMs) play a central role in aligning large language models (LLMs) with human preferences. However, RMs are often sensitive to spurious features such as response length. Existing inference-time approaches for mitigating these…

Great success has been reported using Reinforcement Learning from Human Feedback (RLHF) to align large language models, with open preference datasets enabling wider experimentation, particularly for "helpfulness" in tasks like dialogue and…

Reinforcement learning from human feedback (RLHF) is widely used to align large language models (LLMs) with human preferences. However, RLHF-trained reward models often exhibit length bias -- a systematic tendency to favor longer responses…

Training data quality is one of the most important drivers of final model quality. In this work, we introduce a method for evaluating data integrity based on the assumption that low-quality input prompts result in high variance and low…

Reinforcement Learning from Human Feedback aligns the outputs of Large Language Models with human values and preferences. Central to this process is the reward model (RM), which translates human feedback into training signals for optimising…

The recent rise of Large Reasoning Models (LRMs) has significantly improved multi-step reasoning performance, but often at the cost of generating excessively long reasoning chains. This paper revisits the efficiency of such reasoning…

Large Language Models (LLMs) have become essential in many Natural Language Processing (NLP) tasks, leveraging extensive pre-training and fine-tuning to achieve high accuracy. However, like humans, LLMs exhibit biases, particularly…

Large language models (LLMs) are increasingly deployed via public-facing interfaces to interact with millions of users, each with diverse preferences. Despite this, preference tuning of LLMs predominantly relies on reward models trained…

Offline evaluation of search systems depends on test collections. These benchmarks provide the researchers with a corpus of documents, topics and relevance judgements indicating which documents are relevant for each topic. While test…

Large Language Models (LLMs) with hundreds of billions of parameters have exhibited human-like intelligence by learning from vast amounts of internet-scale data. However, the uninterpretability of large-scale neural networks raises concerns…

In this paper, we study format biases in reinforcement learning from human feedback (RLHF). We observe that many widely-used preference models, including human evaluators, GPT-4, and top-ranking models on the RewardBench benchmark, exhibit…