Papers › Tradeoffs Between Alignment and Helpfulness in Language Models with Representation Engineering

Tradeoffs Between Alignment and Helpfulness in Language Models with Representation Engineering

29 Jan 2024arXiv:2401.16332archive 2025-07-28

Yotam Wolf, Noam Wies, Dorin Shteyman, Binyamin Rothberg, Yoav Levine, Amnon Shashua

Language model alignment has become an important component of AI safety, allowing safe interactions between humans and language models, by enhancing desired behaviors and inhibiting undesired ones. It is often done by tuning the model or inserting preset aligning prompts. Recently, representation engineering, a method which alters the model's behavior via changing its representations post-training, was shown to be effective in aligning LLMs (Zou et al., 2023a). Representation engineering yields gains in alignment oriented tasks such as resistance to adversarial attacks and reduction of social biases, but was also shown to cause a decrease in the ability of the model to perform basic tasks. In this paper we study the tradeoff between the increase in alignment and decrease in helpfulness of the model. We propose a theoretical framework which provides bounds for these two quantities, and demonstrate their relevance empirically. First, we find that under the conditions of our framework, alignment can be guaranteed with representation engineering, and at the same time that helpfulness is harmed in the process. Second, we show that helpfulness is harmed quadratically with the norm of the representation engineering vector, while the alignment increases linearly with it, indicating a regime in which it is efficient to use representation engineering. We validate our findings empirically, and chart the boundaries to the usefulness of representation engineering for alignment.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 9 code samples harvested from 1 repository linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 9 samples from 1 repository, 6 ran (3 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

dorin133/repe_alignment_helpfulness_tradeoff officialmentioned in paperpytorchSyntology: 9 samples, 6 ran (3 instrument-failed) · 3 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

9 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
3ran · our draft was wrong
2ran
3unverified

Licence: 9 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from dorin133/repe_alignment_helpfulness_tradeoff. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

dorin133/repe_alignment_helpfulness_tradeoff official repository 9 samples, 6 ran (3 instrument-failed) · 3 unverified
indices_of_k_most_probable_tokens generate_plots_code/separate_by_dr_visualization.py ran · our draft was wrong no licence file found · pointer only · b300584883c76483 · report fixture: signature logits:Tensor/2/float, k:int/0/int · returned list · level recorded 2026-09-24
initialize_result_containers harmfulness_experiments/harmfulness_helpfulness.py ran · our draft was wrong no licence file found · pointer only · 3a9b9c5f5c4584c2 · report fixture: signature coefficient_range:list/1/float · returned tuple · level recorded 2026-09-24
k_most_common_indices generate_plots_code/separate_by_dr_visualization.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 78ae5c277264f51c · report fixture: signature tensors_list:list/1/int, k:int/0/int · returned list · level recorded 2026-09-24
keys_for_values generate_plots_code/separate_by_dr_visualization.py ran no licence file found · pointer only · 59e79b011501cec4 · report fixture: signature vocabulary:dict/0/?, values:list/1/int · returned list · level recorded 2026-09-24
project_onto_direction in 7 papers repe/rep_readers.py ran · violated contract fingerprinted no licence file found · pointer only · cb6c9ff66d5194bb · report fixture: signature H:ndarray/2/float, direction:ndarray/1/float · returned ndarray · level recorded 2026-09-24
recenter in 5 papers repe/rep_readers.py ran fingerprinted no licence file found · pointer only · f7f3b221cb4cdae8 · report fixture: signature x:Tensor/2/float, mean:NoneType/0/? · returned Tensor · level recorded 2026-09-24
setup_model_and_tokenizer harmfulness_experiments/harmfulness_helpfulness.py unverified no licence file found · pointer only · 33d4b87d6c62162b · report
setup_model_and_tokenizer utils/generate_code_with_REPE.py unverified no licence file found · pointer only · 835f0561c14cf899 · report
setup_model_and_tokenizer fairness_experiments/fairness_safety.py unverified no licence file found · pointer only · f7053de92acde5b9 · report

Tasks

Language Modelling

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections