相关论文: Train-before-Test Harmonizes Language Model Rankin…

Large Language Models (LLMs) offer the potential to automate hiring by matching job descriptions with candidate resumes, streamlining recruitment processes, and reducing operational costs. However, biases inherent in these models may lead…

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…

Reward models (RMs) guide the alignment of large language models (LLMs), steering them toward behaviors preferred by humans. Evaluating RMs is the key to better aligning LLMs. However, the current evaluation of RMs may not directly…

Most language models (LMs) are trained and applied in an autoregressive left-to-right fashion, assuming that the next token only depends on the preceding ones. However, this assumption ignores the potential benefits of using the full…

Recent reinforcement learning (RL) techniques have yielded impressive reasoning improvements in language models, yet it remains unclear whether post-training truly extends a model's reasoning ability beyond what it acquires during…

Large language models (LMs) are currently trained to predict tokens given document prefixes, enabling them to directly perform long-form generation and prompting-style tasks which can be reduced to document completion. Existing pretraining…

Recently, Language Models (LMs) instruction-tuned on multiple tasks, also known as multitask-prompted fine-tuning (MT), have shown the capability to generalize to unseen tasks. Previous work has shown that scaling the number of training…

Existing studies on bias mitigation methods for large language models (LLMs) use diverse baselines and metrics to evaluate debiasing performance, leading to inconsistent comparisons among them. Moreover, their evaluations are mostly based…

Evaluating alignment in language models requires testing how they behave under realistic pressure, not just what they claim they would do. While alignment failures increasingly cause real-world harm, comprehensive evaluation frameworks with…

Large language models (LLMs) exhibit cognitive biases -- systematic tendencies of irrational decision-making, similar to those seen in humans. Prior work has found that these biases vary across models and can be amplified by instruction…

Multilingual Large Language Models (LLMs) exhibit remarkable cross-lingual abilities, yet often exhibit a systematic bias toward the representations from other languages, resulting in semantic interference when generating content in…

Amid the expanding use of pre-training data, the phenomenon of benchmark dataset leakage has become increasingly prominent, exacerbated by opaque training processes and the often undisclosed inclusion of supervised data in contemporary…

Language Models (LMs) have shown promising performance in natural language generation. However, as LMs often generate incorrect or hallucinated responses, it is crucial to correctly quantify their uncertainty in responding to given inputs.…

Modern language models often exhibit powerful but brittle behavior, leading to the development of larger and more diverse benchmarks to reliably assess their behavior. Here, we suggest that model performance can be benchmarked and…

The rapid proliferation of LLMs has created a critical evaluation paradox: while LLMs claim multilingual proficiency, comprehensive non-machine-translated benchmarks exist for fewer than 30 languages, leaving >98% of the world's 7,000…

Reward models (RMs) have driven the state-of-the-art performance of LLMs today by enabling the integration of human feedback into the language modeling process. However, RMs are primarily trained and evaluated in English, and their…

We present a new approach for benchmarking Large Language Model (LLM) capabilities on research-level mathematics. Existing benchmarks largely rely on static, hand-curated sets of contest or textbook-style problems as proxies for…

Value trade-offs are an integral part of human decision-making and language use, however, current tools for interpreting such dynamic and multi-faceted notions of values in language models are limited. In cognitive science, so-called…

While large language models demonstrate remarkable capabilities at task-specific applications through fine-tuning, extending these benefits across diverse languages is essential for broad accessibility. However, effective cross-lingual…

Multi-token prediction (MTP) is a recently proposed pre-training objective for language models. Rather than predicting only the next token (NTP), MTP predicts the next $k$ tokens at each prediction step, using multiple prediction heads. MTP…