REVIEW 6 cited by
From Lists to Emojis: How Format Bias Affects Model Alignment
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
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 strong biases towards specific format patterns, such as lists, links, bold text, and emojis. Furthermore, large language models (LLMs) can exploit these biases to achieve higher rankings on popular benchmarks like AlpacaEval and LMSYS Chatbot Arena. One notable example of this is verbosity bias, where current preference models favor longer responses that appear more comprehensive, even when their quality is equal to or lower than shorter, competing responses. However, format biases beyond verbosity remain largely underexplored in the literature. In this work, we extend the study of biases in preference learning beyond the commonly recognized length bias, offering a comprehensive analysis of a wider range of format biases. Additionally, we show that with a small amount of biased data (less than 1%), we can inject significant bias into the reward model. Moreover, these format biases can also be easily exploited by downstream alignment algorithms, such as best-of-n sampling and online iterative DPO, as it is usually easier to manipulate the format than to improve the quality of responses. Our findings emphasize the need to disentangle format and content both for designing alignment algorithms and evaluating models.
Forward citations
Cited by 6 Pith papers
-
Test-Time Scaling via Error Localization
TTEL uses feedback-induced token probability drops to localize the first error in a failed reasoning trace and branch a new generation from that prefix, improving pass@k per token on coding and math benchmarks.
-
Multi-Turn On-Policy Distillation with Prefix Replay
ReOPD offline-distills multi-turn agentic LLMs via teacher-prefix replay plus step-decay sampling, matching online OPD accuracy at ≥4× speed with zero tool calls.
-
Word Overuse and Alignment in Large Language Models: The Influence of Learning from Human Feedback
People prefer text containing the words that an instruction-tuned model uses far more than its base version, linking human feedback training to LLM word overuse.
-
Model Misalignment and Language Change: Traces of AI-Associated Language in Unscripted Spoken English
After ChatGPT's release, science and tech podcast speakers used AI-associated words like 'surpass' and 'align' more often, while control synonyms showed no average shift.
-
Exploring the Structure of AI-Induced Language Change in Scientific English
In PubMed abstracts, AI-associated 'spiking' words rise together with their synonyms rather than replacing them, and declining words show less systematic, more organic patterns.
-
Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data?
Preference signals in LLM alignment are concentrated in early response tokens, so models trained on data truncated to the first half perform as well as or better than those trained on full responses.
Discussion (0). Sign in to comment.